Prepare 1.0.3 release

We should refer the paper accepted in ICML 2015, instead of arXiv.

.travis.yml

@@ -49,14 +49,16 @@ install:
 
   # install TensorFlow
   - if [[ "$TRAVIS_PYTHON_VERSION" == "2.7" ]]; then
-      pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.6.0-cp27-none-linux_x86_64.whl;
+      pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.7.1-cp27-none-linux_x86_64.whl;
     elif [[ "$TRAVIS_PYTHON_VERSION" == "3.4" ]]; then
-      pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.6.0-cp34-none-linux_x86_64.whl;
+      pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.7.1-cp34-none-linux_x86_64.whl;
     fi
 # command to run tests
 script:
   # run keras backend init to initialize backend config
   - python -c "import keras.backend"
+  # create dataset directory to avoid concurrent directory creation at runtime
+  - mkdir ~/.keras/datasets
   # set up keras backend
   - sed -i -e 's/"backend":[[:space:]]*"[^"]*/"backend":\ "'$KERAS_BACKEND'/g' ~/.keras/keras.json;
   - echo -e "Running tests with the following config:\n$(cat ~/.keras/keras.json)"

ISSUE_TEMPLATE.md

@@ -0,0 +1,9 @@
+Please make sure that the boxes below are checked before you submit your issue. Thank you!
+
+- [ ] Check that you are up-to-date with the master branch of Keras. You can update with:
+pip install git+git://github.com/fchollet/keras.git --upgrade --no-deps
+
+- [ ] If running on Theano, check that you are up-to-date with the master branch of Theano. You can update with:
+pip install git+git://github.com/Theano/Theano.git --upgrade --no-deps
+
+- [ ] Provide a link to a GitHub Gist of a Python script that can reproduce your issue (or just copy the script here if it is short).

README.md

@@ -1,6 +1,7 @@
 # Keras: Deep Learning library for Theano and TensorFlow
 
-![Build status](https://api.travis-ci.org/fchollet/keras.svg)
+[![Build Status](https://travis-ci.org/fchollet/keras.svg?branch=master)](https://travis-ci.org/fchollet/keras)
+[![PyPI version](https://badge.fury.io/py/keras.svg)](https://badge.fury.io/py/keras)
 
 ## You have just found Keras.
 
@@ -37,9 +38,9 @@ Keras is compatible with: __Python 2.7-3.5__.
 
 ## Getting started: 30 seconds to Keras
 
-The core data structure of Keras is a __model__, a way to organize layers. There are two types of models: [`Sequential`](http://keras.io/models/#sequential) and [`Graph`](http://keras.io/models/#graph).
+The core data structure of Keras is a __model__, a way to organize layers. The main type of model is the [`Sequential`](http://keras.io/getting-started/sequential-model-guide) model, a linear stack of layers. For more complex architectures, you should use the [Keras functional API](http://keras.io/getting-started/functional-api-guide).
 
-Here's the `Sequential` model (a linear pile of layers):
+Here's the `Sequential` model:
 
 ```python
 from keras.models import Sequential
@@ -52,15 +53,15 @@ Stacking layers is as easy as `.add()`:
 ```python
 from keras.layers.core import Dense, Activation
 
-model.add(Dense(output_dim=64, input_dim=100, init="glorot_uniform"))
+model.add(Dense(output_dim=64, input_dim=100))
 model.add(Activation("relu"))
-model.add(Dense(output_dim=10, init="glorot_uniform"))
+model.add(Dense(output_dim=10))
 model.add(Activation("softmax"))
 ```
 
 Once your model looks good, configure its learning process with `.compile()`:
 ```python
-model.compile(loss='categorical_crossentropy', optimizer='sgd')
+model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
 ```
 
 If you need to, you can further configure your optimizer. A core principle of Keras is to make things reasonably simple, while allowing the user to be fully in control when they need to (the ultimate control being the easy extensibility of the source code).
@@ -81,7 +82,7 @@ model.train_on_batch(X_batch, Y_batch)
 
 Evaluate your performance in one line:
 ```python
-objective_score = model.evaluate(X_test, Y_test, batch_size=32)
+loss_and_metrics = model.evaluate(X_test, Y_test, batch_size=32)
 ```
 
 Or generate predictions on new data:
@@ -90,11 +91,14 @@ classes = model.predict_classes(X_test, batch_size=32)
 proba = model.predict_proba(X_test, batch_size=32)
 ```
 
-Building a network of LSTMs, a deep CNN, a Neural Turing Machine, a word2vec embedder or any other model is just as fast. The ideas behind deep learning are simple, so why should their implementation be painful?
+Building a question answering system, an image classification model, a Neural Turing Machine, a word2vec embedder or any other model is just as fast. The ideas behind deep learning are simple, so why should their implementation be painful?
 
-Have a look at these [starter examples](http://keras.io/examples/).
+For a more in-depth tutorial about Keras, you can check out:
 
-In the [examples folder](https://github.com/fchollet/keras/tree/master/examples) of the repo, you will find more advanced models: question-answering with memory networks, text generation with stacked LSTMs, neural turing machines, etc.
+- [Getting started with the Sequential model](http://keras.io/getting-started/sequential-model-guide)
+- [Getting started with the functional API](http://keras.io/getting-started/functional-api-guide)
+
+In the [examples folder](https://github.com/fchollet/keras/tree/master/examples) of the repository, you will find more advanced models: question-answering with memory networks, text generation with stacked LSTMs, etc.
 
 
 ------------------
@@ -114,11 +118,6 @@ Keras uses the following dependencies:
 - Theano
     - [See installation instructions](http://deeplearning.net/software/theano/install.html#install).
 
-**Note**: You should use the latest version of Theano, not the PyPI version. Install it with:
-```
-sudo pip install git+git://github.com/Theano/Theano.git
-```
-
 *When using the TensorFlow backend:*
 
 - TensorFlow

docs/autogen.py

@@ -1,9 +1,68 @@
 # -*- coding: utf-8 -*-
+'''
+General documentation architecture:
+
+Home
+Index
+
+- Getting started
+    Getting started with the sequential model
+    Getting started with the functional api
+    Examples
+    FAQ
+    Installation guide
+
+- Models
+    About Keras models
+        explain when one should use Sequential or functional API
+        explain compilation step
+        explain weight saving, weight loading
+        explain serialization, deserialization
+    Sequential
+    Model (functional API)
+
+- Layers
+    About Keras layers
+        explain common layer functions: get_weights, set_weights, get_config
+        explain input_shape
+        explain usage on non-Keras tensors
+    Core layers
+    Convolutional
+    Recurrent
+    Embeddings
+    Normalization
+    Advanced activations
+    Noise
+
+- Preprocessing
+    Image preprocessing
+    Text preprocessing
+    Sequence preprocessing
+
+Objectives
+Optimizers
+Activations
+Callbacks
+Datasets
+Backend
+Initializations
+Regularizers
+Constraints
+Visualization
+Scikit-learn API
+
+'''
 from __future__ import print_function
+from __future__ import unicode_literals
+
 import re
 import inspect
 import os
 import shutil
+import sys
+if sys.version[0] == '2':
+    reload(sys)
+    sys.setdefaultencoding('utf8')
 
 from keras.layers import convolutional
 from keras.layers import recurrent
@@ -11,35 +70,147 @@ from keras.layers import core
 from keras.layers import noise
 from keras.layers import normalization
 from keras.layers import advanced_activations
-from keras.layers import containers
 from keras.layers import embeddings
+from keras.layers import wrappers
 from keras import optimizers
 from keras import callbacks
 from keras import models
+from keras.engine import topology
+from keras import objectives
+from keras import backend
+from keras import constraints
+from keras import activations
+from keras import regularizers
 
-MODULES = [(convolutional, 'keras.layers.convolutional'),
-           (recurrent, 'keras.layers.recurrent'),
-           (noise, 'keras.layers.noise'),
-           (normalization, 'keras.layers.normalization'),
-           (advanced_activations, 'keras.layers.advanced_activations'),
-           (containers, 'keras.layers.containers'),
-           (core, 'keras.layers.core'),
-           (embeddings, 'keras.layers.embeddings'),
-           (optimizers, 'keras.optimizers'),
-           (callbacks, 'keras.callbacks'),
-           (models, 'keras.models')]
+EXCLUDE = {
+    'Optimizer',
+    'Wrapper',
+    'get_session',
+    'set_session',
+}
 
-SKIP = ['build', 'get_params', 'MaskedLayer',
-        'SiameseHead', 'MaskedLambda',
-        'CallbackList']
-ROOT = 'http://keras.io/'
-INCLUDE_METHODS_FOR = [
-    'Layer',
-    'Graph',
-    'Sequential',
-    'Callback',
+PAGES = [
+    {
+        'page': 'models/sequential.md',
+        'functions': [
+            models.Sequential.compile,
+            models.Sequential.fit,
+            models.Sequential.evaluate,
+            models.Sequential.predict,
+            models.Sequential.predict_classes,
+            models.Sequential.predict_proba,
+            models.Sequential.train_on_batch,
+            models.Sequential.test_on_batch,
+            models.Sequential.predict_on_batch,
+            models.Sequential.fit_generator,
+            models.Sequential.evaluate_generator,
+        ],
+    },
+    {
+        'page': 'models/model.md',
+        'functions': [
+            models.Model.compile,
+            models.Model.fit,
+            models.Model.evaluate,
+            models.Model.predict,
+            models.Model.train_on_batch,
+            models.Model.test_on_batch,
+            models.Model.predict_on_batch,
+            models.Model.fit_generator,
+            models.Model.evaluate_generator,
+            models.Model.get_layer,
+        ]
+    },
+    {
+        'page': 'layers/core.md',
+        'classes': [
+            core.Dense,
+            core.Activation,
+            core.Dropout,
+            core.Flatten,
+            core.Reshape,
+            core.Permute,
+            core.RepeatVector,
+            topology.Merge,
+            core.Lambda,
+            core.ActivityRegularization,
+            core.Masking,
+            core.Highway,
+            core.MaxoutDense,
+            core.TimeDistributedDense,
+        ],
+    },
+    {
+        'page': 'layers/convolutional.md',
+        'classes': [
+            convolutional.Convolution1D,
+            convolutional.Convolution2D,
+            convolutional.Convolution3D,
+            convolutional.MaxPooling1D,
+            convolutional.MaxPooling2D,
+            convolutional.MaxPooling3D,
+            convolutional.AveragePooling1D,
+            convolutional.AveragePooling2D,
+            convolutional.AveragePooling3D,
+            convolutional.UpSampling1D,
+            convolutional.UpSampling2D,
+            convolutional.UpSampling3D,
+            convolutional.ZeroPadding1D,
+            convolutional.ZeroPadding2D,
+            convolutional.ZeroPadding3D,
+        ],
+    },
+    {
+        'page': 'layers/recurrent.md',
+        'classes': [
+            recurrent.Recurrent,
+            recurrent.SimpleRNN,
+            recurrent.GRU,
+            recurrent.LSTM,
+        ],
+    },
+    {
+        'page': 'layers/embeddings.md',
+        'classes': [
+            embeddings.Embedding,
+        ],
+    },
+    {
+        'page': 'layers/normalization.md',
+        'classes': [
+            normalization.BatchNormalization,
+        ],
+    },
+    {
+        'page': 'layers/advanced-activations.md',
+        'all_module_classes': [advanced_activations],
+    },
+    {
+        'page': 'layers/noise.md',
+        'all_module_classes': [noise],
+    },
+    {
+        'page': 'layers/wrappers.md',
+        'all_module_classes': [wrappers],
+    },
+
+
+    {
+        'page': 'optimizers.md',
+        'all_module_classes': [optimizers],
+    },
+    {
+        'page': 'callbacks.md',
+        'all_module_classes': [callbacks],
+    },
+    {
+        'page': 'backend.md',
+        'all_module_functions': [backend],
+    },
 ]
 
+ROOT = 'http://keras.io/'
+
 
 def get_earliest_class_that_defined_member(member, cls):
     ancestors = get_classes_ancestors([cls])
@@ -67,23 +238,24 @@ def get_classes_ancestors(classes):
         return filtered_ancestors
 
 
-def get_method_signature(method):
-    signature = inspect.getargspec(method)
+def get_function_signature(function, method=True):
+    signature = inspect.getargspec(function)
     defaults = signature.defaults
-    args = signature.args[1:]
+    if method:
+        args = signature.args[1:]
+    else:
+        args = signature.args
     if defaults:
         kwargs = zip(args[-len(defaults):], defaults)
         args = args[:-len(defaults)]
     else:
         kwargs = []
-    st = '%s.%s(' % (method.__module__, method.__name__)
+    st = '%s.%s(' % (function.__module__, function.__name__)
     for a in args:
         st += str(a) + ', '
     for a, v in kwargs:
         if type(v) == str:
             v = '\'' + v + '\''
-        elif type(v) == unicode:
-            v = 'u\'' + v + '\''
         st += str(a) + '=' + str(v) + ', '
     if kwargs or args:
         return st[:-2] + ')'
@@ -91,6 +263,17 @@ def get_method_signature(method):
         return st + ')'
 
 
+def get_class_signature(cls):
+    try:
+        class_signature = get_function_signature(cls.__init__)
+        class_signature = class_signature.replace('__init__', cls.__name__)
+    except:
+        # in case the class inherits from object and does not
+        # define __init__
+        class_signature = cls.__module__ + '.' + cls.__name__ + '()'
+    return class_signature
+
+
 def class_to_docs_link(cls):
     module_name = cls.__module__
     assert module_name[:6] == 'keras.'
@@ -124,19 +307,26 @@ def process_class_docstring(docstring):
     docstring = re.sub(r'    ([^\s\\]+):(.*)\n',
                        r'    - __\1__:\2\n',
                        docstring)
+
+    docstring = docstring.replace('    ' * 5, '\t\t')
     docstring = docstring.replace('    ' * 3, '\t')
     docstring = docstring.replace('    ', '')
     return docstring
 
 
-def process_method_docstring(docstring):
-    docstring = re.sub(r'    # (.*)\n',
-                       r'    __\1__\n\n',
+def process_function_docstring(docstring):
+    docstring = re.sub(r'\n    # (.*)\n',
+                       r'\n    __\1__\n\n',
+                       docstring)
+    docstring = re.sub(r'\n        # (.*)\n',
+                       r'\n        __\1__\n\n',
                        docstring)
 
     docstring = re.sub(r'    ([^\s\\]+):(.*)\n',
                        r'    - __\1__:\2\n',
                        docstring)
+
+    docstring = docstring.replace('    ' * 6, '\t\t')
     docstring = docstring.replace('    ' * 4, '\t')
     docstring = docstring.replace('    ', '')
     return docstring
@@ -156,101 +346,175 @@ for subdir, dirs, fnames in os.walk('templates'):
             shutil.copy(fpath, new_fpath)
 
 print('Starting autogeneration.')
-covered_so_far = set()
-for module, module_name in MODULES:
-    class_pages = []
-    for name in dir(module):
-        if name in SKIP:
-            continue
-        if name[0] == '_':
-            continue
-        module_member = getattr(module, name)
-        if module_member in covered_so_far:
-            continue
-        if inspect.isclass(module_member):
-            cls = module_member
-            if cls.__module__ == module_name:
+for page_data in PAGES:
+    blocks = []
+    classes = page_data.get('classes', [])
+    for module in page_data.get('all_module_classes', []):
+        module_classes = []
+        for name in dir(module):
+            if name[0] == '_' or name in EXCLUDE:
+                continue
+            module_member = getattr(module, name)
+            if inspect.isclass(module_member):
+                cls = module_member
+                if cls.__module__ == module.__name__:
+                    if cls not in module_classes:
+                        module_classes.append(cls)
+        module_classes.sort(key=lambda x: id(x))
+        classes += module_classes
 
-                try:
-                    class_signature = get_method_signature(cls.__init__)
-                    class_signature = class_signature.replace('__init__', cls.__name__)
-                except:
-                    # in case the class inherits from object and does not
-                    # define __init__
-                    class_signature = module_name + '.' + cls.__name__ + '()'
+    for cls in classes:
+        subblocks = []
+        signature = get_class_signature(cls)
+        subblocks.append('<span style="float:right;">' + class_to_source_link(cls) + '</span>')
+        subblocks.append('### ' + cls.__name__ + '\n')
+        subblocks.append(code_snippet(signature))
+        docstring = cls.__doc__
+        if docstring:
+            subblocks.append(process_class_docstring(docstring))
+        blocks.append('\n'.join(subblocks))
 
-                methods = []
-                methods_not_defined_here = []
-                for name in dir(cls):
-                    if name in SKIP:
-                        continue
-                    if name[0] == '_':
-                        continue
-                    cls_member = getattr(cls, name)
-                    if inspect.ismethod(cls_member):
-                        method = cls_member
-                        signature = inspect.getargspec(method)
-                        defaults = signature.defaults
-                        args = signature.args[1:]
-                        if defaults:
-                            kwargs = zip(args[-len(defaults):], defaults)
-                            args = args[:-len(defaults)]
-                        else:
-                            kwargs = []
+    functions = page_data.get('functions', [])
+    for module in page_data.get('all_module_functions', []):
+        module_functions = []
+        for name in dir(module):
+            if name[0] == '_' or name in EXCLUDE:
+                continue
+            module_member = getattr(module, name)
+            if inspect.isfunction(module_member):
+                function = module_member
+                if module.__name__ in function.__module__:
+                    if function not in module_functions:
+                        module_functions.append(function)
+        module_functions.sort(key=lambda x: id(x))
+        functions += module_functions
 
-                        defined_by = get_earliest_class_that_defined_member(method.__name__, cls)
-                        if cls == defined_by:
-                            methods.append(method)
-                        else:
-                            methods_not_defined_here.append((method, defined_by))
-
-                blocks = []
-                blocks.append('<span style="float:right;">' + class_to_source_link(cls) + '</span>')
-                blocks.append('# ' + cls.__name__ + '\n')
-                blocks.append(code_snippet(class_signature))
-                docstring = cls.__doc__
-                if docstring:
-                    blocks.append(process_class_docstring(docstring))
-
-                if cls.__name__ in INCLUDE_METHODS_FOR:
-                    if methods or methods_not_defined_here:
-                        blocks.append('### Methods\n')
-                        for method in methods:
-                            signature = get_method_signature(method)
-                            signature = signature.replace(module_name + '.', '')
-                            blocks.append(code_snippet(signature))
-                            docstring = method.__doc__
-                            if docstring:
-                                blocks.append(process_method_docstring(docstring))
-                        for method, defined_by in methods_not_defined_here:
-                            signature = get_method_signature(method)
-                            method_module_name = method.__module__
-                            signature = signature.replace(method_module_name + '.', '')
-                            link = '[' + defined_by.__name__ + '](' + class_to_docs_link(defined_by) + ')'
-                            blocks.append(code_snippet(signature))
-                            blocks.append('Defined by ' + link + '.\n')
-
-                mkdown = '\n'.join(blocks)
-                class_pages.append((id(cls), mkdown))
-                covered_so_far.add(module_member)
-
-    class_pages.sort(key=lambda x: x[0])
-    class_pages = [x[1] for x in class_pages]
-    module_page = '\n----\n\n'.join(class_pages)
+    for function in functions:
+        subblocks = []
+        signature = get_function_signature(function, method=False)
+        signature = signature.replace(function.__module__ + '.', '')
+        subblocks.append('### ' + function.__name__ + '\n')
+        subblocks.append(code_snippet(signature))
+        docstring = function.__doc__
+        if docstring:
+            subblocks.append(process_function_docstring(docstring))
+            blocks.append('\n\n'.join(subblocks))
 
+    mkdown = '\n----\n\n'.join(blocks)
     # save module page.
     # Either insert content into existing page,
     # or create page otherwise
-    path = 'sources/' + module_name.replace('.', '/')[6:] + '.md'
+    page_name = page_data['page']
+    path = os.path.join('sources', page_name)
     if os.path.exists(path):
         template = open(path).read()
         assert '{{autogenerated}}' in template, ('Template found for ' + path +
                                                  ' but missing {{autogenerated}} tag.')
-        module_page = template.replace('{{autogenerated}}', module_page)
+        mkdown = template.replace('{{autogenerated}}', mkdown)
         print('...inserting autogenerated content into template:', path)
     else:
         print('...creating new page with autogenerated content:', path)
     subdir = os.path.dirname(path)
     if not os.path.exists(subdir):
         os.makedirs(subdir)
-    open(path, 'w').write(module_page)
+    open(path, 'w').write(mkdown)
+
+
+# covered_so_far = set()
+# for module, module_name in MODULES:
+#     class_pages = []
+#     for name in dir(module):
+#         if name in SKIP:
+#             continue
+#         if name[0] == '_':
+#             continue
+#         module_member = getattr(module, name)
+#         if module_member in covered_so_far:
+#             continue
+#         if inspect.isclass(module_member):
+#             cls = module_member
+#             if cls.__module__ == module_name:
+
+#                 try:
+#                     class_signature = get_function_signature(cls.__init__)
+#                     class_signature = class_signature.replace('__init__', cls.__name__)
+#                 except:
+#                     # in case the class inherits from object and does not
+#                     # define __init__
+#                     class_signature = module_name + '.' + cls.__name__ + '()'
+
+#                 functions = []
+#                 functions_not_defined_here = []
+#                 for name in dir(cls):
+#                     if name in SKIP:
+#                         continue
+#                     if name[0] == '_':
+#                         continue
+#                     cls_member = getattr(cls, name)
+#                     if inspect.isfunction(cls_member):
+#                         function = cls_member
+#                         signature = inspect.getargspec(function)
+#                         defaults = signature.defaults
+#                         args = signature.args[1:]
+#                         if defaults:
+#                             kwargs = zip(args[-len(defaults):], defaults)
+#                             args = args[:-len(defaults)]
+#                         else:
+#                             kwargs = []
+
+#                         defined_by = get_earliest_class_that_defined_member(function.__name__, cls)
+#                         if cls == defined_by:
+#                             functions.append(function)
+#                         else:
+#                             functions_not_defined_here.append((function, defined_by))
+
+#                 blocks = []
+#                 blocks.append('<span style="float:right;">' + class_to_source_link(cls) + '</span>')
+#                 blocks.append('# ' + cls.__name__ + '\n')
+#                 blocks.append(code_snippet(class_signature))
+#                 docstring = cls.__doc__
+#                 if docstring:
+#                     blocks.append(process_class_docstring(docstring))
+
+#                 if cls.__name__ in INCLUDE_functionS_FOR:
+#                     if functions or functions_not_defined_here:
+#                         blocks.append('### functions\n')
+#                         for function in functions:
+#                             signature = get_function_signature(function)
+#                             signature = signature.replace(module_name + '.', '')
+#                             blocks.append(code_snippet(signature))
+#                             docstring = function.__doc__
+#                             if docstring:
+#                                 blocks.append(process_function_docstring(docstring))
+#                         for function, defined_by in functions_not_defined_here:
+#                             signature = get_function_signature(function)
+#                             function_module_name = function.__module__
+#                             signature = signature.replace(function_module_name + '.', '')
+#                             link = '[' + defined_by.__name__ + '](' + class_to_docs_link(defined_by) + ')'
+#                             blocks.append(code_snippet(signature))
+#                             blocks.append('Defined by ' + link + '.\n')
+
+#                 mkdown = '\n'.join(blocks)
+#                 class_pages.append((id(cls), mkdown))
+#                 covered_so_far.add(module_member)
+
+#     class_pages.sort(key=lambda x: x[0])
+#     class_pages = [x[1] for x in class_pages]
+#     module_page = '\n----\n\n'.join(class_pages)
+
+#     # save module page.
+#     # Either insert content into existing page,
+#     # or create page otherwise
+#     path = 'sources/' + module_name.replace('.', '/')[6:] + '.md'
+#     if os.path.exists(path):
+#         template = open(path).read()
+#         assert '{{autogenerated}}' in template, ('Template found for ' + path +
+#                                                  ' but missing {{autogenerated}} tag.')
+#         module_page = template.replace('{{autogenerated}}', module_page)
+#         print('...inserting autogenerated content into template:', path)
+#     else:
+#         print('...creating new page with autogenerated content:', path)
+#     subdir = os.path.dirname(path)
+#     if not os.path.exists(subdir):
+#         os.makedirs(subdir)
+#     open(path, 'w').write(module_page)

docs/mkdocs.yml

@@ -3,8 +3,8 @@ theme: readthedocs
 docs_dir: sources
 repo_url: http://github.com/fchollet/keras
 site_url: http://keras.io/
-#theme_dir: theme
-site_description: Documentation for fast and lightweight Keras Deep Learning library.
+# theme_dir: theme
+site_description: 'Documentation for Keras, the Python Deep Learning library.'
 
 dev_addr: '0.0.0.0:8000'
 google_analytics: ['UA-61785484-1', 'keras.io']
@@ -12,31 +12,41 @@ google_analytics: ['UA-61785484-1', 'keras.io']
 
 pages:
 - Home: index.md
-- Index: documentation.md
-- Examples: examples.md
-- FAQ: faq.md
-- Backends: backend.md
-- Optimizers: optimizers.md
-- Objectives: objectives.md
-- Models: models.md
-- Activations: activations.md
-- Initializations: initializations.md
-- Regularizers: regularizers.md
-- Constraints: constraints.md
-- Callbacks: callbacks.md
-- Datasets: datasets.md
-- Visualization: visualization.md
+- Getting started:
+  - Guide to the Sequential model: getting-started/sequential-model-guide.md
+  - Guide to the Functional API: getting-started/functional-api-guide.md
+  - FAQ: getting-started/faq.md
+- Models:
+  - About Keras models: models/about-keras-models.md
+  - Sequential: models/sequential.md
+  - Model (functional API): models/model.md
 - Layers:
+  - About Keras layers: layers/about-keras-layers.md
   - Core Layers: layers/core.md
   - Convolutional Layers: layers/convolutional.md
   - Recurrent Layers: layers/recurrent.md
-  - Advanced Activations Layers: layers/advanced_activations.md
-  - Normalization Layers: layers/normalization.md
   - Embedding Layers: layers/embeddings.md
+  - Advanced Activations Layers: layers/advanced-activations.md
+  - Normalization Layers: layers/normalization.md
   - Noise layers: layers/noise.md
-  - Containers: layers/containers.md
+  - Layer wrappers: layers/wrappers.md
+  - Writing your own Keras layers: layers/writing-your-own-keras-layers.md
 - Preprocessing:
   - Sequence Preprocessing: preprocessing/sequence.md
   - Text Preprocessing: preprocessing/text.md
   - Image Preprocessing: preprocessing/image.md
+- Objectives: objectives.md
+- Optimizers: optimizers.md
+- Activations: activations.md
+- Callbacks: callbacks.md
+- Datasets: datasets.md
+- Backend: backend.md
+- Initializations: initializations.md
+- Regularizers: regularizers.md
+- Constraints: constraints.md
+- Visualization: visualization.md
+- Scikit-learn API: scikit-learn-api.md
+
+
+
 

docs/templates/activations.md

@@ -14,11 +14,13 @@ is equivalent to:
 model.add(Dense(64, activation='tanh'))
 ```
 
-You can also pass an element-wise Theano function as an activation:
+You can also pass an element-wise Theano/TensorFlow function as an activation:
 
 ```python
+from keras import backend as K
+
 def tanh(x):
-    return theano.tensor.tanh(x)
+    return K.tanh(x)
 
 model.add(Dense(64, activation=tanh))
 model.add(Activation(tanh))
@@ -28,6 +30,7 @@ model.add(Activation(tanh))
 
 - __softmax__: Softmax applied across inputs last dimension. Expects shape either `(nb_samples, nb_timesteps, nb_dims)` or `(nb_samples, nb_dims)`.
 - __softplus__
+- __softsign__
 - __relu__
 - __tanh__
 - __sigmoid__
@@ -36,4 +39,4 @@ model.add(Activation(tanh))
 
 ## On Advanced Activations
 
-Activations that are more complex than a simple Theano function (eg. learnable activations, configurable activations, etc.) are available as [Advanced Activation layers](layers/advanced_activations.md), and can be found in the module `keras.layers.advanced_activations`. These include PReLU and LeakyReLU.
+Activations that are more complex than a simple Theano/TensorFlow function (eg. learnable activations, configurable activations, etc.) are available as [Advanced Activation layers](layers/advanced-activations.md), and can be found in the module `keras.layers.advanced_activations`. These include PReLU and LeakyReLU.

docs/templates/backend.md

@@ -9,6 +9,8 @@ At this time, Keras has two backend implementations available: the **Theano** ba
 - [Theano](http://deeplearning.net/software/theano/) is an open-source symbolic tensor manipulation framework developed by LISA/MILA Lab at Université de Montréal.
 - [TensorFlow](http://www.tensorflow.org/) is an open-source symbolic tensor manipulation framework developed by Google, Inc.
 
+----
+
 ## Switching from one backend to another
 
 If you have run Keras at least once, you will find the Keras configuration file at:
@@ -32,6 +34,8 @@ Using TensorFlow backend.
 tensorflow
 ```
 
+----
+
 ## Using the abstract Keras backend to write new code
 
 If you want the Keras modules you write to be compatible with both Theano and TensorFlow, you have to write them via the abstract Keras backend API. Here's an intro.
@@ -74,8 +78,12 @@ a = concatenate([b, c], axis=-1)
 # etc...
 ```
 
-For more information, see the code at `keras/backend/theano_backend.py` and `keras/backend/tensorflow_backend.py`.
-
+----
+
+## Backend functions
+
+
+{{autogenerated}}
 
 
 

docs/templates/datasets.md

@@ -2,13 +2,13 @@
 
 ## CIFAR10 small image classification
 
-`keras.datasets.cifar10`
-
 Dataset of 50,000 32x32 color training images, labeled over 10 categories, and 10,000 test images.
 
 ### Usage:
 
 ```python
+from keras.datasets import cifar10
+
 (X_train, y_train), (X_test, y_test) = cifar10.load_data()
 ```
 
@@ -21,13 +21,13 @@ Dataset of 50,000 32x32 color training images, labeled over 10 categories, and 1
 
 ## CIFAR100 small image classification
 
-`keras.datasets.cifar100`
-
 Dataset of 50,000 32x32 color training images, labeled over 100 categories, and 10,000 test images.
 
 ### Usage:
 
 ```python
+from keras.datasets import cifar100
+
 (X_train, y_train), (X_test, y_test) = cifar100.load_data(label_mode='fine')
 ```
 
@@ -44,8 +44,6 @@ Dataset of 50,000 32x32 color training images, labeled over 100 categories, and
 
 ## IMDB Movie reviews sentiment classification
 
-`keras.datasets.imdb`
-
 Dataset of 25,000 movies reviews from IMDB, labeled by sentiment (positive/negative). Reviews have been preprocessed, and each review is encoded as a [sequence](preprocessing/sequence.md) of word indexes (integers). For convenience, words are indexed by overall frequency in the dataset, so that for instance the integer "3" encodes the 3rd most frequent word in the data. This allows for quick filtering operations such as: "only consider the top 10,000 most common words, but eliminate the top 20 most common words".
 
 As a convention, "0" does not stand for a specific word, but instead is used to encode any unknown word.
@@ -53,8 +51,13 @@ As a convention, "0" does not stand for a specific word, but instead is used to
 ### Usage:
 
 ```python
-(X_train, y_train), (X_test, y_test) = imdb.load_data(path="imdb.pkl", \
-nb_words=None, skip_top=0, maxlen=None, test_split=0.1, seed=113)
+from keras.datasets import imdb
+
+(X_train, y_train), (X_test, y_test) = imdb.load_data(path="imdb.pkl",
+                                                      nb_words=None,
+                                                      skip_top=0,
+                                                      maxlen=None,
+                                                      test_split=0.1)
 ```
 - __Return:__
     - 2 tuples:
@@ -74,15 +77,18 @@ nb_words=None, skip_top=0, maxlen=None, test_split=0.1, seed=113)
 
 ## Reuters newswire topics classification
 
-`keras.datasets.reuters`
-
 Dataset of 11,228 newswires from Reuters, labeled over 46 topics. As with the IMDB dataset, each wire is encoded as a sequence of word indexes (same conventions).
 
 ### Usage:
 
 ```python
-(X_train, y_train), (X_test, y_test) = reuters.load_data(path="reuters.pkl", \
-nb_words=None, skip_top=0, maxlen=None, test_split=0.1, seed=113)
+from keras.datasets import reuters
+
+(X_train, y_train), (X_test, y_test) = reuters.load_data(path="reuters.pkl",
+                                                         nb_words=None,
+                                                         skip_top=0,
+                                                         maxlen=None,
+                                                         test_split=0.1)
 ```
 
 The specifications are the same as that of the IMDB dataset.
@@ -101,13 +107,13 @@ word_index = reuters.get_word_index(path="reuters_word_index.pkl")
     
 ## MNIST database of handwritten digits
 
-`keras.datasets.mnist`
-
 Dataset of 60,000 28x28 grayscale images of the 10 digits, along with a test set of 10,000 images.
 
 ### Usage:
 
 ```python
+from keras.datasets import mnist
+
 (X_train, y_train), (X_test, y_test) = mnist.load_data()
 ```
 

docs/templates/documentation.md

@@ -1,40 +0,0 @@
-# Keras Documentation Index
-
-## Introduction
-
-- [Home](index.md)
-- [Index](documentation.md)
-- [Examples](examples.md)
-- [FAQ](faq.md)
-- [Backend](backend.md)
-
----
-
-## Base functionality
-
-- [Optimizers](optimizers.md)
-- [Objectives](objectives.md)
-- [Models](models.md)
-- [Activations](activations.md)
-- [Initializations](initializations.md)
-- [Regularizers](regularizers.md)
-- [Constraints](constraints.md)
-- [Callbacks](callbacks.md)
-- [Datasets](datasets.md)
-
----
-
-## Layers
-- [Core](layers/core.md)
-- [Convolutional](layers/convolutional.md)
-- [Recurrent](layers/recurrent.md)
-- [Advanced Activations](layers/advanced_activations.md)
-- [Normalization](layers/normalization.md)
-- [Embeddings](layers/embeddings.md)
-
----
-
-## Preprocessing
-- [Sequence](preprocessing/sequence.md)
-- [Text](preprocessing/text.md)
-- [Image](preprocessing/image.md)

docs/templates/examples.md

@@ -1,197 +0,0 @@
-
-Here are a few examples to get you started!
-
-### Multilayer Perceptron (MLP) for multi-class softmax classification:
-
-```python
-from keras.models import Sequential
-from keras.layers import Dense, Dropout, Activation
-from keras.optimizers import SGD
-
-model = Sequential()
-# Dense(64) is a fully-connected layer with 64 hidden units.
-# in the first layer, you must specify the expected input data shape:
-# here, 20-dimensional vectors.
-model.add(Dense(64, input_dim=20, init='uniform'))
-model.add(Activation('tanh'))
-model.add(Dropout(0.5))
-model.add(Dense(64, init='uniform'))
-model.add(Activation('tanh'))
-model.add(Dropout(0.5))
-model.add(Dense(10, init='uniform'))
-model.add(Activation('softmax'))
-
-sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
-model.compile(loss='categorical_crossentropy',
-              optimizer=sgd)
-
-model.fit(X_train, y_train,
-          nb_epoch=20,
-          batch_size=16,
-          show_accuracy=True)
-score = model.evaluate(X_test, y_test, batch_size=16)
-```
-
-### Alternative implementation of a similar MLP:
-
-```python
-model = Sequential()
-model.add(Dense(64, input_dim=20, activation='relu'))
-model.add(Dropout(0.5))
-model.add(Dense(64, activation='relu'))
-model.add(Dropout(0.5))
-model.add(Dense(10, activation='softmax'))
-
-model.compile(loss='categorical_crossentropy', optimizer='adadelta')
-```
-
-
-### MLP for binary classification:
-```python
-model = Sequential()
-model.add(Dense(64, input_dim=20, init='uniform', activation='relu'))
-model.add(Dropout(0.5))
-model.add(Dense(64, activation='relu'))
-model.add(Dropout(0.5))
-model.add(Dense(1, activation='sigmoid'))
-
-# "class_mode" defaults to "categorical". For correctly displaying accuracy
-# in a binary classification problem, it should be set to "binary".
-model.compile(loss='binary_crossentropy',
-              optimizer='rmsprop',
-              class_mode='binary')
-```
-
-### VGG-like convnet:
-
-```python
-from keras.models import Sequential
-from keras.layers import Dense, Dropout, Activation, Flatten
-from keras.layers import Convolution2D, MaxPooling2D
-from keras.optimizers import SGD
-
-model = Sequential()
-# input: 100x100 images with 3 channels -> (3, 100, 100) tensors.
-# this applies 32 convolution filters of size 3x3 each.
-model.add(Convolution2D(32, 3, 3, border_mode='valid', input_shape=(3, 100, 100)))
-model.add(Activation('relu'))
-model.add(Convolution2D(32, 3, 3))
-model.add(Activation('relu'))
-model.add(MaxPooling2D(pool_size=(2, 2)))
-model.add(Dropout(0.25))
-
-model.add(Convolution2D(64, 3, 3, border_mode='valid'))
-model.add(Activation('relu'))
-model.add(Convolution2D(64, 3, 3))
-model.add(Activation('relu'))
-model.add(MaxPooling2D(pool_size=(2, 2)))
-model.add(Dropout(0.25))
-
-model.add(Flatten())
-# Note: Keras does automatic shape inference.
-model.add(Dense(256))
-model.add(Activation('relu'))
-model.add(Dropout(0.5))
-
-model.add(Dense(10))
-model.add(Activation('softmax'))
-
-sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
-model.compile(loss='categorical_crossentropy', optimizer=sgd)
-
-model.fit(X_train, Y_train, batch_size=32, nb_epoch=1)
-
-```
-
-### Sequence classification with LSTM:
-
-```python
-from keras.models import Sequential
-from keras.layers import Dense, Dropout, Activation
-from keras.layers import Embedding
-from keras.layers import LSTM
-
-model = Sequential()
-model.add(Embedding(max_features, 256, input_length=maxlen))
-model.add(LSTM(output_dim=128, activation='sigmoid', inner_activation='hard_sigmoid'))
-model.add(Dropout(0.5))
-model.add(Dense(1))
-model.add(Activation('sigmoid'))
-
-model.compile(loss='binary_crossentropy', optimizer='rmsprop')
-
-model.fit(X_train, Y_train, batch_size=16, nb_epoch=10)
-score = model.evaluate(X_test, Y_test, batch_size=16)
-```
-
-### Architecture for learning image captions with a convnet and a Gated Recurrent Unit:
-(word-level embedding, caption of maximum length 16 words).
-
-Note that getting this to work well will require using a bigger convnet, initialized with pre-trained weights.
-
-```python
-max_caption_len = 16
-vocab_size = 10000
-
-# first, let's define an image model that
-# will encode pictures into 128-dimensional vectors.
-# it should be initialized with pre-trained weights.
-image_model = Sequential()
-image_model.add(Convolution2D(32, 3, 3, border_mode='valid', input_shape=(3, 100, 100)))
-image_model.add(Activation('relu'))
-image_model.add(Convolution2D(32, 3, 3))
-image_model.add(Activation('relu'))
-image_model.add(MaxPooling2D(pool_size=(2, 2)))
-
-image_model.add(Convolution2D(64, 3, 3, border_mode='valid'))
-image_model.add(Activation('relu'))
-image_model.add(Convolution2D(64, 3, 3))
-image_model.add(Activation('relu'))
-image_model.add(MaxPooling2D(pool_size=(2, 2)))
-
-image_model.add(Flatten())
-image_model.add(Dense(128))
-
-# let's load the weights from a save file.
-image_model.load_weights('weight_file.h5')
-
-# next, let's define a RNN model that encodes sequences of words
-# into sequences of 128-dimensional word vectors.
-language_model = Sequential()
-language_model.add(Embedding(vocab_size, 256, input_length=max_caption_len))
-language_model.add(GRU(output_dim=128, return_sequences=True))
-language_model.add(TimeDistributedDense(128))
-
-# let's repeat the image vector to turn it into a sequence.
-image_model.add(RepeatVector(max_caption_len))
-
-# the output of both models will be tensors of shape (samples, max_caption_len, 128).
-# let's concatenate these 2 vector sequences.
-model = Merge([image_model, language_model], mode='concat', concat_axis=-1)
-# let's encode this vector sequence into a single vector
-model.add(GRU(256, 256, return_sequences=False))
-# which will be used to compute a probability
-# distribution over what the next word in the caption should be!
-model.add(Dense(vocab_size))
-model.add(Activation('softmax'))
-
-model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
-
-# "images" is a numpy float array of shape (nb_samples, nb_channels=3, width, height).
-# "captions" is a numpy integer array of shape (nb_samples, max_caption_len)
-# containing word index sequences representing partial captions.
-# "next_words" is a numpy float array of shape (nb_samples, vocab_size)
-# containing a categorical encoding (0s and 1s) of the next word in the corresponding
-# partial caption.
-model.fit([images, partial_captions], next_words, batch_size=16, nb_epoch=100)
-```
-
-In the examples folder, you will find example models for real datasets:
-
-- CIFAR10 small images classification: Convolutional Neural Network (CNN) with realtime data augmentation
-- IMDB movie review sentiment classification: LSTM over sequences of words
-- Reuters newswires topic classification: Multilayer Perceptron (MLP)
-- MNIST handwritten digits classification: MLP & CNN
-- Character-level text generation with LSTM
-
-...and more.

docs/templates/getting-started/faq.md

@@ -1,29 +1,39 @@
 # Keras FAQ: Frequently Asked Keras Questions
 
-[How can I run Keras on GPU?](#how-can-i-run-keras-on-gpu)
-
-[How can I save a Keras model?](#how-can-i-save-a-keras-model)
-
-[Why is the training loss much higher than the testing loss?](#why-is-the-training-loss-much-higher-than-the-testing-loss)
-
-[How can I visualize the output of an intermediate layer?](#how-can-i-visualize-the-output-of-an-intermediate-layer)
-
-[How can I use Keras with datasets that don't fit in memory?](#how-can-i-use-keras-with-datasets-that-dont-fit-in-memory)
-
-[How can I interrupt training when the validation loss isn't decreasing anymore?](#how-can-i-interrupt-training-when-the-validation-loss-isnt-decreasing-anymore)
-
-[How is the validation split computed?](#how-is-the-validation-split-computed)
-
-[Is the data shuffled during training?](#is-the-data-shuffled-during-training)
-
-[How can I record the training / validation loss / accuracy at each epoch?](#how-can-i-record-the-training-validation-loss-accuracy-at-each-epoch)
-
-[How can I use stateful RNNs?](#how-can-i-use-stateful-rnns)
+- [How should I cite Keras?](#how-should-i-cite-keras)
+- [How can I run Keras on GPU?](#how-can-i-run-keras-on-gpu)
+- [How can I save a Keras model?](#how-can-i-save-a-keras-model)
+- [Why is the training loss much higher than the testing loss?](#why-is-the-training-loss-much-higher-than-the-testing-loss)
+- [How can I visualize the output of an intermediate layer?](#how-can-i-visualize-the-output-of-an-intermediate-layer)
+- [How can I use Keras with datasets that don't fit in memory?](#how-can-i-use-keras-with-datasets-that-dont-fit-in-memory)
+- [How can I interrupt training when the validation loss isn't decreasing anymore?](#how-can-i-interrupt-training-when-the-validation-loss-isnt-decreasing-anymore)
+- [How is the validation split computed?](#how-is-the-validation-split-computed)
+- [Is the data shuffled during training?](#is-the-data-shuffled-during-training)
+- [How can I record the training / validation loss / accuracy at each epoch?](#how-can-i-record-the-training-validation-loss-accuracy-at-each-epoch)
+- [How can I use stateful RNNs?](#how-can-i-use-stateful-rnns)
 
 ---
 
+### How should I cite Keras?
+
+Please cite Keras in your publications if it helps your research. Here is an example BibTeX entry:
+
+```
+@misc{chollet2015keras,
+  author = {Chollet, Francois},
+  title = {Keras},
+  year = {2015},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/fchollet/keras}}
+}
+```
+
 ### How can I run Keras on GPU?
 
+If you are running on the TensorFlow backend, your code will automatically run on GPU if any available GPU is detected.
+If you are running on the Theano backend, you can use one of the following methods:
+
 Method 1: use Theano flags.
 ```bash
 THEANO_FLAGS=device=gpu,floatX=float32 python my_keras_script.py
@@ -67,7 +77,10 @@ model = model_from_json(json_string)
 model = model_from_yaml(yaml_string)
 ```
 
-If you need to save the weights of a model, you can do so in HDF5:
+If you need to save the weights of a model, you can do so in HDF5 with the code below.
+
+Note that you will first need to install HDF5 and the Python library h5py, which do not come bundled with Keras.
+
 ```python
 model.save_weights('my_model_weights.h5')
 ```
@@ -89,6 +102,11 @@ model = model_from_json(open('my_model_architecture.json').read())
 model.load_weights('my_model_weights.h5')
 ```
 
+Finally, before it can be used, the model shall be compiled.
+```python
+model.compile(optimizer='adagrad', loss='mse')
+```
+
 ---
 
 ### Why is the training loss much higher than the testing loss?
@@ -108,22 +126,47 @@ from keras import backend as K
 
 # with a Sequential model
 get_3rd_layer_output = K.function([model.layers[0].input],
-                                  [model.layers[3].get_output(train=False)])
+                                  [model.layers[3].output])
 layer_output = get_3rd_layer_output([X])[0]
-
-# with a Graph model
-get_conv_layer_output = K.function([model.inputs[i].input for i in model.input_order],
-                                   [model.nodes['conv'].get_output(train=False)])
-conv_output = get_conv_layer_output([input_data_dict[i] for i in model.input_order])[0]
 ```
 
 Similarly, you could build a Theano and TensorFlow function directly.
 
+Note that if your model has a different behavior in training and testing phase (e.g. if it uses `Dropout`, `BatchNormalization`, etc.), you will need
+to pass the learning phase flag to your function:
+
+```python
+get_3rd_layer_output = K.function([model.layers[0].input, K.learning_phase()],
+                                  [model.layers[3].output])
+
+# output in test mode = 0
+layer_output = get_3rd_layer_output([X, 0])[0]
+
+# output in train mode = 1
+layer_output = get_3rd_layer_output([X, 1])[0]
+```
+
+Another more flexible way of getting output from intermediate layers is to use the [functional API](/getting-started/functional-api-guide). For example, if you have created an autoencoder for MNIST:
+
+```python
+inputs = Input(shape=(784,))
+encoded = Dense(32, activation='relu')(inputs)
+decoded = Dense(784)(encoded)
+model = Model(input=inputs, output=decoded)
+```
+
+After compiling and training the model, you can get the output of the data from the encoder like this:
+
+```python
+encoder = Model(input=inputs, output=encoded)
+X_encoded = encoder.predict(X)
+```
+
 ---
 
 ### How can I use Keras with datasets that don't fit in memory?
 
-You can do batch training using `model.train_on_batch(X, y)` and `model.test_on_batch(X, y)`. See the [models documentation](models.md).
+You can do batch training using `model.train_on_batch(X, y)` and `model.test_on_batch(X, y)`. See the [models documentation](/models/sequential).
 
 Alternatively, you can write a generator that yields batches of training data and use the method `model.fit_generator(data_generator, samples_per_epoch, nb_epoch)`.
 
@@ -141,7 +184,7 @@ early_stopping = EarlyStopping(monitor='val_loss', patience=2)
 model.fit(X, y, validation_split=0.2, callbacks=[early_stopping])
 ```
 
-Find out more in the [callbacks documentation](callbacks.md).
+Find out more in the [callbacks documentation](/callbacks).
 
 ---
 
@@ -156,14 +199,14 @@ If you set the `validation_split` argument in `model.fit` to e.g. 0.1, then the
 
 Yes, if the `shuffle` argument in `model.fit` is set to `True` (which is the default), the training data will be randomly shuffled at each epoch.
 
-Validation data isn't shuffled.
+Validation data is never shuffled.
 
 ---
 
 
 ### How can I record the training / validation loss / accuracy at each epoch?
 
-The `model.fit` method returns an `History` callback, which has a `history` attribute containing the lists of successive losses / accuracies.
+The `model.fit` method returns an `History` callback, which has a `history` attribute containing the lists of successive losses and other metrics.
 
 ```python
 hist = model.fit(X, y, validation_split=0.2)

docs/templates/getting-started/functional-api-guide.md

@@ -0,0 +1,421 @@
+# Getting started with the Keras functional API
+
+The Keras functional API is the way to go for defining complex models, such as multi-output models, directed acyclic graphs, or models with shared layers.
+
+This guide assumes that you are already familiar with the `Sequential` model.
+
+Let's start with something simple.
+
+-----
+
+## First example: fully connected network
+
+The `Sequential` model is probably a better choice to implement such a network, but it helps to start with something really simple.
+
+- A layer instance is callable (on a tensor), and it returns a tensor
+- Input tensor(s) and output tensor(s) can then be used to define a `Model`
+- Such a model can be trained just like Keras `Sequential` models.
+
+```python
+from keras.layers import Input, Dense
+from keras.models import Model
+
+# this returns a tensor
+inputs = Input(shape=(784,))
+
+# a layer instance is callable on a tensor, and returns a tensor
+x = Dense(64, activation='relu')(inputs)
+x = Dense(64, activation='relu')(x)
+predictions = Dense(10, activation='softmax')(x)
+
+# this creates a model that includes
+# the Input layer and three Dense layers
+model = Model(input=inputs, output=predictions)
+model.compile(optimizer='rmsprop',
+              loss='categorical_crossentropy',
+              metrics=['accuracy'])
+model.fit(data, labels)  # starts training
+```
+
+-----
+
+## All models are callable, just like layers
+
+With the functional API, it is easy to re-use trained models: you can treat any model as if it were a layer, by calling it on a tensor. Note that by calling a model you aren't just re-using the *architecture* of the model, you are also re-using its weights.
+
+```python
+x = Input(shape=(784,))
+# this works, and returns the 10-way softmax we defined above.
+y = model(x)
+```
+
+This can allow, for instance, to quickly create models that can process *sequences* of inputs. You could turn an image classification model into a video classification model, in just one line.
+
+```python
+from keras.layers import TimeDistributed
+
+# input tensor for sequences of 20 timesteps,
+# each containing a 784-dimensional vector
+input_sequences = Input(shape=(20, 784))
+
+# this applies our previous model to every timestep in the input sequences.
+# the output of the previous model was a 10-way softmax,
+# so the output of the layer below will be a sequence of 20 vectors of size 10.
+processed_sequences = TimeDistributed(model)(input_sequences)
+```
+
+-----
+
+## Multi-input and multi-output models
+
+Here's a good use case for the functional API: models with multiple inputs and outputs. The functional API makes it easy to manipulate a large number of intertwined datastreams.
+
+Let's consider the following model. We seek to predict how many retweets and likes a news headline will receive on Twitter. The main input to the model will be the headline itself, as a sequence of words, but to spice things up, our model will also have an auxiliary input, receiving extra data such as the time of day when the headline was posted, etc.
+The model will also be supervised via two loss functions. Using the main loss function earlier in a model is a good regularization mechanism for deep models.
+
+Here's what our model looks like:
+
+<img src="http://s3.amazonaws.com/keras.io/img/multi-input-multi-output-graph.png" alt="multi-input-multi-output-graph" style="width: 400px;"/>
+
+Let's implement it with the functional API.
+
+The main input will receive the headline, as a sequence of integers (each integer encodes a word).
+The integers will be between 1 and 10,000 (a vocabulary of 10,000 words) and the sequences will be 100 words long.
+
+```python
+from keras.layers import Input, Embedding, LSTM, Dense, merge
+from keras.models import Model
+
+# headline input: meant to receive sequences of 100 integers, between 1 and 10000.
+# note that we can name any layer by passing it a "name" argument.
+main_input = Input(shape=(100,), dtype='int32', name='main_input')
+
+# this embedding layer will encode the input sequence
+# into a sequence of dense 512-dimensional vectors.
+x = Embedding(output_dim=512, input_dim=10000, input_length=100)(main_input)
+
+# a LSTM will transform the vector sequence into a single vector,
+# containing information about the entire sequence
+lstm_out = LSTM(32)(x)
+```
+
+Here we insert the auxiliary loss, allowing the LSTM and Embedding layer to be trained smoothly even though the main loss will be much higher in the model.
+
+```python
+auxiliary_loss = Dense(1, activation='sigmoid', name='aux_output')(lstm_out)
+```
+
+At this point, we feed into the model our auxiliary input data by concatenating it with the LSTM output:
+
+```python
+auxiliary_input = Input(shape=(5,), name='aux_input')
+x = merge([lstm_out, auxiliary_input], mode='concat')
+
+# we stack a deep fully-connected network on top
+x = Dense(64, activation='relu')(x)
+x = Dense(64, activation='relu')(x)
+x = Dense(64, activation='relu')(x)
+
+# and finally we add the main logistic regression layer
+main_loss = Dense(1, activation='sigmoid', name='main_output')(x)
+```
+
+This defines a model with two inputs and two outputs:
+
+```python
+model = Model(input=[main_input, auxiliary_input], output=[main_loss, auxiliary_loss])
+```
+
+We compile the model and assign a weight of 0.2 to the auxiliary loss.
+To specify different `loss_weights` or `loss` for each different output, you can use a list or a dictionary.
+Here we pass a single loss as the `loss` argument, so the same loss will be used on all outputs.
+
+```python
+model.compile(optimizer='rmsprop', loss='binary_crossentropy',
+              loss_weights=[1., 0.2])
+```
+
+We can train the model by passing it lists of input arrays and target arrays:
+
+```python
+model.fit([headline_data, additional_data], [labels, labels],
+          nb_epoch=50, batch_size=32)
+```
+
+Since our inputs and outputs are named (we passed them a "name" argument),
+We could also have compiled the model via:
+
+```python
+model.compile(optimizer='rmsprop',
+              loss={'main_output': 'binary_crossentropy', 'aux_output': 'binary_crossentropy'},
+              loss_weights={'main_output': 1., 'aux_output': 0.2})
+
+# and trained it via:
+model.fit({'main_input': headline_data, 'aux_input': additional_data},
+          {'main_output': labels, 'aux_output': labels},
+          nb_epoch=50, batch_size=32)
+```
+
+-----
+
+## Shared layers
+
+Another good use for the functional API are models that use shared layers. Let's take a look at shared layers.
+
+Let's consider a dataset of tweets. We want to build a model that can tell whether two tweets are from the same person or not (this can allow us to compare users by the similarity of their tweets, for instance).
+
+One way to achieve this is to build a model that encodes two tweets into two vectors, concatenates the vectors and adds a logistic regression of top, outputting a probability that the two tweets share the same author. The model would then be trained on positive tweet pairs and negative tweet pairs.
+
+Because the problem is symetric, the mechanism that encodes the first tweet should be reused (weights and all) to encode the second tweet. Here we use a shared LSTM layer to encode the tweets.
+
+Let's build this with the functional API. We will take as input for a tweet a binary matrix of shape `(140, 256)`, i.e. a sequence of 140 vectors of size 256, where each dimension in the 256-dimensional vector encodes the presence/absence of a character (out of an alphabet of 256 frequent characters).
+
+```python
+from keras.layers import Input, LSTM, Dense, merge
+from keras.models import Model
+
+tweet_a = Input(shape=(140, 256))
+tweet_b = Input(shape=(140, 256))
+```
+
+To share a layer across different inputs, simply instantiate the layer once, then call it on as many inputs as you want:
+
+```python
+# this layer can take as input a matrix
+# and will return a vector of size 64
+shared_lstm = LSTM(64)
+
+# when we reuse the same layer instance
+# multiple times, the weights of the layer
+# are also being reused
+# (it is effectively *the same* layer)
+encoded_a = shared_lstm(tweet_a)
+encoded_b = shared_lstm(tweet_b)
+
+# we can then concatenate the two vectors:
+merged_vector = merge([encoded_a, encoded_b], mode='concat', concat_axis=-1)
+
+# and add a logistic regression on top
+predictions = Dense(1, activation='sigmoid')(merged_vector)
+
+# we define a trainable model linking the
+# tweet inputs to the predictions
+model = Model(input=[tweet_a, tweet_b], output=predictions)
+
+model.compile(optimizer='rmsprop',
+              loss='binary_crossentropy',
+              metrics=['accuracy'])
+model.fit([data_a, data_b], labels, nb_epoch=10)
+```
+
+Let's pause to take a look at how to read the shared layer's output or output shape.
+
+-----
+
+## The concept of layer "node"
+
+Whenever you are calling a layer on some input, you are creating a new tensor (the output of the layer), and you are adding a "node" to the layer, linking the input tensor to the output tensor. When you are calling the same layer multiple times, that layer owns multiple nodes indexed as 0, 1, 2...
+
+In previous versions of Keras, you could obtain the output tensor of a layer instance via `layer.get_output()`, or its output shape via `layer.output_shape`. You still can (except `get_output()` has been replaced by the property `output`). But what if a layer is connected to multiple inputs?
+
+As long as a layer is only connected to one input, there is no confusion, and `.output` will return the one output of the layer:
+
+```python
+a = Input(shape=(140, 256))
+
+lstm = LSTM(32)
+encoded_a = lstm(a)
+
+assert lstm.output == encoded_a
+```
+
+Not so if the layer has multiple inputs:
+```python
+a = Input(shape=(140, 256))
+b = Input(shape=(140, 256))
+
+lstm = LSTM(32)
+encoded_a = lstm(a)
+encoded_b = lstm(b)
+
+lstm.output
+```
+```
+>> AssertionError: Layer lstm_1 has multiple inbound nodes,
+hence the notion of "layer output" is ill-defined.
+Use `get_output_at(node_index)` instead.
+```
+
+Okay then. The following works:
+
+```python
+assert lstm.get_output_at(0) == encoded_a
+assert lstm.get_output_at(1) == encoded_b
+```
+
+Simple enough, right?
+
+The same is true for the properties `input_shape` and `output_shape`: as long as the layer has only one node, or as long as all nodes have the same input/output shape, then the notion of "layer output/input shape" is well defined, and that one shape will be returned by `layer.output_shape`/`layer.input_shape`. But if, for instance, you apply a same `Convolution2D` layer to an input of shape `(3, 32, 32)`, and then to an input of shape `(3, 64, 64)`, the layer will have multiple input/output shapes, and you will have to fetch them by specifying the index of the node they belong to:
+
+```python
+a = Input(shape=(3, 32, 32))
+b = Input(shape=(3, 64, 64))
+
+conv = Convolution2D(16, 3, 3, border_mode='same')
+conved_a = conv(a)
+
+# only one input so far, the following will work:
+assert conv.input_shape == (None, 3, 32, 32)
+
+conved_b = conv(b)
+# now the `.input_shape` property wouldn't work, but this does:
+assert conv.get_input_shape_at(0) == (None, 3, 32, 32)
+assert conv.get_input_shape_at(1) == (None, 3, 64, 64)
+```
+
+-----
+
+## More examples
+
+Code examples are still the best way to get started, so here are a few more.
+
+### Inception module
+
+For more information about the Inception architecture, see [Going Deeper with Convolutions](http://arxiv.org/abs/1409.4842).
+
+```python
+from keras.layers import merge, Convolution2D, MaxPooling2D, Input
+
+input_img = Input(shape=(3, 256, 256))
+
+tower_1 = Convolution2D(64, 1, 1, border_mode='same', activation='relu')(input_img)
+tower_1 = Convolution2D(64, 3, 3, border_mode='same', activation='relu')(tower_1)
+
+tower_2 = Convolution2D(64, 1, 1, border_mode='same', activation='relu')(input_img)
+tower_2 = Convolution2D(64, 5, 5, border_mode='same', activation='relu')(tower_2)
+
+tower_3 = MaxPooling2D((3, 3), strides=(1, 1), border_mode='same')(input_img)
+tower_3 = Convolution2D(64, 1, 1, border_mode='same', activation='relu')(tower_3)
+
+output = merge([tower_1, tower_2, tower_3], mode='concat', concat_axis=1)
+```
+
+### Residual connection on a convolution layer
+
+For more information about residual networks, see [Deep Residual Learning for Image Recognition](http://arxiv.org/abs/1512.03385).
+
+```python
+from keras.layers import merge, Convolution2D, Input
+
+# input tensor for a 3-channel 256x256 image
+x = Input(shape=(3, 256, 256))
+# 3x3 conv with 3 output channels (same as input channels)
+y = Convolution2D(3, 3, 3, border_mode='same')
+# this returns x + y.
+z = merge([x, y], mode='sum')
+```
+
+### Shared vision model
+
+This model re-uses the same image-processing module on two inputs, to classify whether two MNIST digits are the same digit or different digits.
+
+```python
+from keras.layers import merge, Convolution2D, MaxPooling2D, Input, Dense, Flatten
+from keras.models import Model
+
+# first, define the vision modules
+digit_input = Input(shape=(1, 27, 27))
+x = Convolution2D(64, 3, 3)(digit_input)
+x = Convolution2D(64, 3, 3)(x)
+x = MaxPooling2D((2, 2))(x)
+out = Flatten()(x)
+
+vision_model = Model(digit_input, out)
+
+# then define the tell-digits-apart model
+digit_a = Input(shape=(1, 27, 27))
+digit_b = Input(shape=(1, 27, 27))
+
+# the vision model will be shared, weights and all
+out_a = vision_model(digit_a)
+out_b = vision_model(digit_b)
+
+concatenated = merge([out_a, out_b], mode='concat')
+out = Dense(1, activation='sigmoid')(concatenated)
+
+classification_model = Model([digit_a, digit_b], out)
+```
+
+### Visual question answering model
+
+This model can select the correct one-word answer when asked a natural-language question about a picture.
+
+It works by encoding the question into a vector, encoding the image into a vector, concatenating the two, and training on top a logistic regression over some vocabulary of potential answers.
+
+```python
+from keras.layers import Convolution2D, MaxPooling2D, Flatten
+from keras.layers import Input, LSTM, Embedding, Dense, merge
+from keras.models import Model, Sequential
+
+# first, let's define a vision model using a Sequential model.
+# this model will encode an image into a vector.
+vision_model = Sequential()
+vision_model.add(Convolution2D(64, 3, 3, activation='relu', border_mode='same', input_shape=(3, 224, 224)))
+vision_model.add(Convolution2D(64, 3, 3, activation='relu'))
+vision_model.add(MaxPooling2D((2, 2)))
+vision_model.add(Convolution2D(128, 3, 3, activation='relu', border_mode='same'))
+vision_model.add(Convolution2D(128, 3, 3, activation='relu'))
+vision_model.add(MaxPooling2D((2, 2)))
+vision_model.add(Convolution2D(256, 3, 3, activation='relu', border_mode='same'))
+vision_model.add(Convolution2D(256, 3, 3, activation='relu'))
+vision_model.add(Convolution2D(256, 3, 3, activation='relu'))
+vision_model.add(MaxPooling2D((2, 2)))
+vision_model.add(Flatten())
+
+# now let's get a tensor with the output of our vision model:
+image_input = Input(shape=(3, 224, 224))
+encoded_image = vision_model(image_input)
+
+# next, let's define a language model to encode the question into a vector.
+# each question will be at most 100 word long,
+# and we will index words as integers from 1 to 9999.
+question_input = Input(shape=(100,), dtype='int32')
+embedded_question = Embedding(input_dim=10000, output_dim=256, input_length=100)(question_input)
+encoded_question = LSTM(256)(embedded_question)
+
+# let's concatenate the question vector and the image vector:
+merged = merge([encoded_question, encoded_image], mode='concat')
+
+# and let's train a logistic regression over 1000 words on top:
+output = Dense(1000, activation='softmax')(merged)
+
+# this is our final model:
+vqa_model = Model(input=[image_input, question_input], output=output)
+
+# the next stage would be training this model on actual data.
+```
+
+### Video question answering model
+
+Now that we have trained our image QA model, we can quickly turn it into a video QA model. With appropriate training, you will be able to show it a short video (e.g. 100-frame human action) and ask a natural language question about the video (e.g. "what sport is the boy playing?" -> "football").
+
+```python
+from keras.layers import TimeDistributed
+
+video_input = Input(shape=(100, 3, 224, 224))
+# this is our video encoded via the previously trained vision_model (weights are reused)
+encoded_frame_sequence = TimeDistributed(vision_model)(video_input)  # the output will be a sequence of vectors
+encoded_video = LSTM(256)(encoded_frame_sequence)  # the output will be a vector
+
+# this is a model-level representation of the question encoder, reusing the same weights as before:
+question_encoder = Model(input=question_input, output=encoded_question)
+
+# let's use it to encode the question:
+video_question_input = Input(shape=(100,), dtype='int32')
+encoded_video_question = question_encoder(video_question_input)
+
+# and this is our video question answering model:
+merged = merge([encoded_video, encoded_video_question], mode='concat')
+output = Dense(1000, activation='softmax')(merged)
+video_qa_model = Model(input=[video_input, video_question_input], output=output)
+```

docs/templates/getting-started/sequential-model-guide.md

@@ -0,0 +1,541 @@
+# Getting started with the Keras Sequential model
+
+The `Sequential` model is a linear stack of layers.
+
+You can create a `Sequential` model by passing a list of layer instances to the constructor:
+
+```python
+from keras.models import Sequential
+
+model = Sequential([
+    Dense(32, input_dim=784),
+    Activation('relu'),
+    Dense(10),
+    Activation('softmax'),
+])
+```
+
+You can also simply add layers via the `.add()` method:
+
+```python
+model = Sequential()
+model.add(Dense(32, input_dim=784))
+model.add(Activation('relu'))
+```
+
+----
+
+## Specifying the input shape
+
+The model needs to know what input shape it should expect. For this reason, the first layer in a `Sequential` model (and only the first, because following layers can do automatic shape inference) needs to receive information about its input shape. There are several possible ways to do this:
+
+- pass an `input_shape` argument to the first layer. This is a shape tuple (a tuple of integers or `None` entries, where `None` indicates that any positive integer may be expected). In `input_shape`, the batch dimension is not included.
+- pass instead a `batch_input_shape` argument, where the batch dimension is included. This is useful for specifying a fixed batch size (e.g. with stateful RNNs).
+- some 2D layers, such as `Dense`, support the specification of their input shape via the argument `input_dim`, and some 3D temporal layers support the arguments `input_dim` and `input_length`.
+
+As such, the following three snippets are strictly equivalent:
+```python
+model = Sequential()
+model.add(Dense(32, input_shape=(784,)))
+```
+```python
+model = Sequential()
+model.add(Dense(32, batch_input_shape=(None, 784)))
+# note that batch dimension is "None" here,
+# so the model will be able to process batches of any size.
+```
+```python
+model = Sequential()
+model.add(Dense(32, input_dim=784))
+```
+
+And so are the following three snippets:
+```python
+model = Sequential()
+model.add(LSTM(32, input_shape=(10, 64)))
+```
+```python
+model = Sequential()
+model.add(LSTM(32, batch_input_shape=(None, 10, 64)))
+```
+```python
+model = Sequential()
+model.add(LSTM(32, input_length=10, input_dim=64))
+```
+
+----
+
+## The Merge layer
+
+Multiple `Sequential` instances can be merged into a single output via a `Merge` layer. The output is a layer that can be added as first layer in a new `Sequential` model. For instance, here's a model with two separate input branches getting merged:
+
+```python
+from keras.layers import Merge
+
+left_branch = Sequential()
+left_branch.add(Dense(32, input_dim=784))
+
+right_branch = Sequential()
+right_branch.add(Dense(32, input_dim=784))
+
+merged = Merge([left_branch, right_branch], mode='concat')
+
+final_model = Sequential()
+final_model.add(merged)
+final_model.add(Dense(10, activation='softmax'))
+```
+
+<img src="http://s3.amazonaws.com/keras.io/img/two_branches_sequential_model.png" alt="two branch Sequential" style="width: 400px;"/>
+
+The `Merge` layer supports a number of pre-defined modes:
+
+- `sum` (default): element-wise sum
+- `concat`: tensor concatenation. You can specify the concatenation axis via the argument `concat_axis`.
+- `mul`: element-wise multiplication
+- `ave`: tensor average
+- `dot`: dot product. You can specify which axes to reduce along via the argument `dot_axes`.
+- `cos`: cosine proximity between vectors in 2D tensors.
+
+You can also pass a function as the `mode` argument, allowing for arbitrary transformations:
+
+```python
+merged = Merge([left_branch, right_branch], mode=lambda x, y: x - y)
+```
+
+Now you know enough to be able to define *almost* any model with Keras. For complex models that cannot be expressed via `Sequential` and `Merge`, you can use [the functional API](/getting-started/functional-api-guide).
+
+
+----
+
+## Compilation
+
+Before training a model, you need to configure the learning process, which is done via the `compile` method. It receives three arguments:
+
+- an optimizer. This could be the string identifier of an existing optimizer (such as `rmsprop` or `adagrad`), or an instance of the `Optimizer` class. See: [optimizers](/optimizers).
+- a loss function. This is the objective that the model will try to minimize. It can be the string identifier of an existing loss function (such as `categorical_crossentropy` or `mse`), or it can be an objective function. See: [objectives](/objectives).
+- a list of metrics. For any classification problem you will want to set this to `metrics=['accuracy']`. A metric could be the string identifier of an existing metric (only `accuracy` is supported at this point), or a custom metric function.
+
+```python
+# for a multi-class classification problem
+model.compile(optimizer='rmsprop',
+              loss='categorical_crossentropy',
+              metrics=['accuracy'])
+
+# for a binary classification problem
+model.compile(optimizer='rmsprop',
+              loss='binary_crossentropy',
+              metrics=['accuracy'])
+
+# for a mean squared error regression problem
+model.compile(optimizer='rmsprop',
+              loss='mse')
+```
+
+----
+
+## Training
+
+Keras models are trained on Numpy arrays of input data and labels. For training a model, you will typically use the `fit` function. [Read its documentation here](/models/sequential). 
+
+```python
+# for a single-input model with 2 classes (binary):
+
+model = Sequential()
+model.add(Dense(1, input_dim=784, activation='softmax'))
+model.compile(optimizer='rmsprop',
+              loss='binary_crossentropy',
+              metrics=['accuracy'])
+
+# generate dummy data
+import numpy as np
+data = np.random.random((1000, 784))
+labels = np.random.randint(2, size=(1000, 1))
+
+# train the model, iterating on the data in batches
+# of 32 samples
+model.fit(data, labels, nb_epoch=10, batch_size=32)
+```
+```python
+# for a multi-input model with 10 classes:
+
+left_branch = Sequential()
+left_branch.add(Dense(32, input_dim=784))
+
+right_branch = Sequential()
+right_branch.add(Dense(32, input_dim=784))
+
+merged = Merge([left_branch, right_branch], mode='concat')
+
+model = Sequential()
+model.add(merged)
+model.add(Dense(10, activation='softmax'))
+
+model.compile(optimizer='rmsprop',
+              loss='categorical_crossentropy',
+              metrics=['accuracy'])
+
+# generate dummy data
+import numpy as np
+from keras.utils.np_utils import to_categorical
+data_1 = np.random.random((1000, 784))
+data_2 = np.random.random((1000, 784))
+
+# these are integers between 0 and 9
+labels = np.random.randint(10, size=(1000, 1))
+# we convert the labels to a binary matrix of size (1000, 10)
+# for use with categorical_crossentropy
+labels = to_categorical(labels, 10)
+
+# train the model
+# note that we are passing a list of Numpy arrays as training data
+# since the model has 2 inputs
+model.fit([data_1, data_2], labels, nb_epoch=10, batch_size=32)
+```
+
+----
+
+
+## Examples
+
+Here are a few examples to get you started!
+
+In the examples folder, you will also find example models for real datasets:
+
+- CIFAR10 small images classification: Convolutional Neural Network (CNN) with realtime data augmentation
+- IMDB movie review sentiment classification: LSTM over sequences of words
+- Reuters newswires topic classification: Multilayer Perceptron (MLP)
+- MNIST handwritten digits classification: MLP & CNN
+- Character-level text generation with LSTM
+
+...and more.
+
+
+### Multilayer Perceptron (MLP) for multi-class softmax classification:
+
+```python
+from keras.models import Sequential
+from keras.layers import Dense, Dropout, Activation
+from keras.optimizers import SGD
+
+model = Sequential()
+# Dense(64) is a fully-connected layer with 64 hidden units.
+# in the first layer, you must specify the expected input data shape:
+# here, 20-dimensional vectors.
+model.add(Dense(64, input_dim=20, init='uniform'))
+model.add(Activation('tanh'))
+model.add(Dropout(0.5))
+model.add(Dense(64, init='uniform'))
+model.add(Activation('tanh'))
+model.add(Dropout(0.5))
+model.add(Dense(10, init='uniform'))
+model.add(Activation('softmax'))
+
+sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
+model.compile(loss='categorical_crossentropy',
+              optimizer=sgd,
+              metrics=['accuracy'])
+
+model.fit(X_train, y_train,
+          nb_epoch=20,
+          batch_size=16)
+score = model.evaluate(X_test, y_test, batch_size=16)
+```
+
+
+### Alternative implementation of a similar MLP:
+
+```python
+model = Sequential()
+model.add(Dense(64, input_dim=20, activation='relu'))
+model.add(Dropout(0.5))
+model.add(Dense(64, activation='relu'))
+model.add(Dropout(0.5))
+model.add(Dense(10, activation='softmax'))
+
+model.compile(loss='categorical_crossentropy',
+              optimizer='adadelta',
+              metrics=['accuracy'])
+```
+
+
+### MLP for binary classification:
+```python
+model = Sequential()
+model.add(Dense(64, input_dim=20, init='uniform', activation='relu'))
+model.add(Dropout(0.5))
+model.add(Dense(64, activation='relu'))
+model.add(Dropout(0.5))
+model.add(Dense(1, activation='sigmoid'))
+
+model.compile(loss='binary_crossentropy',
+              optimizer='rmsprop',
+              metrics=['accuracy'])
+```
+
+
+### VGG-like convnet:
+
+```python
+from keras.models import Sequential
+from keras.layers import Dense, Dropout, Activation, Flatten
+from keras.layers import Convolution2D, MaxPooling2D
+from keras.optimizers import SGD
+
+model = Sequential()
+# input: 100x100 images with 3 channels -> (3, 100, 100) tensors.
+# this applies 32 convolution filters of size 3x3 each.
+model.add(Convolution2D(32, 3, 3, border_mode='valid', input_shape=(3, 100, 100)))
+model.add(Activation('relu'))
+model.add(Convolution2D(32, 3, 3))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Dropout(0.25))
+
+model.add(Convolution2D(64, 3, 3, border_mode='valid'))
+model.add(Activation('relu'))
+model.add(Convolution2D(64, 3, 3))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Dropout(0.25))
+
+model.add(Flatten())
+# Note: Keras does automatic shape inference.
+model.add(Dense(256))
+model.add(Activation('relu'))
+model.add(Dropout(0.5))
+
+model.add(Dense(10))
+model.add(Activation('softmax'))
+
+sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
+model.compile(loss='categorical_crossentropy', optimizer=sgd)
+
+model.fit(X_train, Y_train, batch_size=32, nb_epoch=1)
+```
+
+
+### Sequence classification with LSTM:
+
+```python
+from keras.models import Sequential
+from keras.layers import Dense, Dropout, Activation
+from keras.layers import Embedding
+from keras.layers import LSTM
+
+model = Sequential()
+model.add(Embedding(max_features, 256, input_length=maxlen))
+model.add(LSTM(output_dim=128, activation='sigmoid', inner_activation='hard_sigmoid'))
+model.add(Dropout(0.5))
+model.add(Dense(1))
+model.add(Activation('sigmoid'))
+
+model.compile(loss='binary_crossentropy',
+              optimizer='rmsprop',
+              metrics=['accuracy'])
+
+model.fit(X_train, Y_train, batch_size=16, nb_epoch=10)
+score = model.evaluate(X_test, Y_test, batch_size=16)
+```
+
+### Architecture for learning image captions with a convnet and a Gated Recurrent Unit:
+(word-level embedding, caption of maximum length 16 words).
+
+Note that getting this to work well will require using a bigger convnet, initialized with pre-trained weights.
+
+```python
+max_caption_len = 16
+vocab_size = 10000
+
+# first, let's define an image model that
+# will encode pictures into 128-dimensional vectors.
+# it should be initialized with pre-trained weights.
+image_model = Sequential()
+image_model.add(Convolution2D(32, 3, 3, border_mode='valid', input_shape=(3, 100, 100)))
+image_model.add(Activation('relu'))
+image_model.add(Convolution2D(32, 3, 3))
+image_model.add(Activation('relu'))
+image_model.add(MaxPooling2D(pool_size=(2, 2)))
+
+image_model.add(Convolution2D(64, 3, 3, border_mode='valid'))
+image_model.add(Activation('relu'))
+image_model.add(Convolution2D(64, 3, 3))
+image_model.add(Activation('relu'))
+image_model.add(MaxPooling2D(pool_size=(2, 2)))
+
+image_model.add(Flatten())
+image_model.add(Dense(128))
+
+# let's load the weights from a save file.
+image_model.load_weights('weight_file.h5')
+
+# next, let's define a RNN model that encodes sequences of words
+# into sequences of 128-dimensional word vectors.
+language_model = Sequential()
+language_model.add(Embedding(vocab_size, 256, input_length=max_caption_len))
+language_model.add(GRU(output_dim=128, return_sequences=True))
+language_model.add(TimeDistributedDense(128))
+
+# let's repeat the image vector to turn it into a sequence.
+image_model.add(RepeatVector(max_caption_len))
+
+# the output of both models will be tensors of shape (samples, max_caption_len, 128).
+# let's concatenate these 2 vector sequences.
+model = Sequential()
+model.add(Merge([image_model, language_model], mode='concat', concat_axis=-1))
+# let's encode this vector sequence into a single vector
+model.add(GRU(256, return_sequences=False))
+# which will be used to compute a probability
+# distribution over what the next word in the caption should be!
+model.add(Dense(vocab_size))
+model.add(Activation('softmax'))
+
+model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
+
+# "images" is a numpy float array of shape (nb_samples, nb_channels=3, width, height).
+# "captions" is a numpy integer array of shape (nb_samples, max_caption_len)
+# containing word index sequences representing partial captions.
+# "next_words" is a numpy float array of shape (nb_samples, vocab_size)
+# containing a categorical encoding (0s and 1s) of the next word in the corresponding
+# partial caption.
+model.fit([images, partial_captions], next_words, batch_size=16, nb_epoch=100)
+```
+
+
+### Stacked LSTM for sequence classification
+
+In this model, we stack 3 LSTM layers on top of each other,
+making the model capable of learning higher-level temporal representations.
+
+The first two LSTMs return their full output sequences, but the last one only returns
+the last step in its output sequence, thus dropping the temporal dimension
+(i.e. converting the input sequence into a single vector).
+
+<img src="http://keras.io/img/regular_stacked_lstm.png" alt="stacked LSTM" style="width: 300px;"/>
+
+```python
+from keras.models import Sequential
+from keras.layers import LSTM, Dense
+import numpy as np
+
+data_dim = 16
+timesteps = 8
+nb_classes = 10
+
+# expected input data shape: (batch_size, timesteps, data_dim)
+model = Sequential()
+model.add(LSTM(32, return_sequences=True,
+               input_shape=(timesteps, data_dim)))  # returns a sequence of vectors of dimension 32
+model.add(LSTM(32, return_sequences=True))  # returns a sequence of vectors of dimension 32
+model.add(LSTM(32))  # return a single vector of dimension 32
+model.add(Dense(10, activation='softmax'))
+
+model.compile(loss='categorical_crossentropy',
+              optimizer='rmsprop',
+              metrics=['accuracy'])
+
+# generate dummy training data
+x_train = np.random.random((1000, timesteps, data_dim))
+y_train = np.random.random((1000, nb_classes))
+
+# generate dummy validation data
+x_val = np.random.random((100, timesteps, data_dim))
+y_val = np.random.random((100, nb_classes))
+
+model.fit(x_train, y_train,
+          batch_size=64, nb_epoch=5,
+          validation_data=(x_val, y_val))
+```
+
+
+### Same stacked LSTM model, rendered "stateful"
+
+A stateful recurrent model is one for which the internal states (memories) obtained after processing a batch
+of samples are reused as initial states for the samples of the next batch. This allows to process longer sequences
+while keeping computational complexity manageable.
+
+[You can read more about stateful RNNs in the FAQ.](/faq/#how-can-i-use-stateful-rnns)
+
+```python
+from keras.models import Sequential
+from keras.layers import LSTM, Dense
+import numpy as np
+
+data_dim = 16
+timesteps = 8
+nb_classes = 10
+batch_size = 32
+
+# expected input batch shape: (batch_size, timesteps, data_dim)
+# note that we have to provide the full batch_input_shape since the network is stateful.
+# the sample of index i in batch k is the follow-up for the sample i in batch k-1.
+model = Sequential()
+model.add(LSTM(32, return_sequences=True, stateful=True,
+               batch_input_shape=(batch_size, timesteps, data_dim)))
+model.add(LSTM(32, return_sequences=True, stateful=True))
+model.add(LSTM(32, stateful=True))
+model.add(Dense(10, activation='softmax'))
+
+model.compile(loss='categorical_crossentropy',
+              optimizer='rmsprop',
+              metrics=['accuracy'])
+
+# generate dummy training data
+x_train = np.random.random((batch_size * 10, timesteps, data_dim))
+y_train = np.random.random((batch_size * 10, nb_classes))
+
+# generate dummy validation data
+x_val = np.random.random((batch_size * 3, timesteps, data_dim))
+y_val = np.random.random((batch_size * 3, nb_classes))
+
+model.fit(x_train, y_train,
+          batch_size=batch_size, nb_epoch=5,
+          validation_data=(x_val, y_val))
+```
+
+
+### Two merged LSTM encoders for classification over two parallel sequences
+
+In this model, two input sequences are encoded into vectors by two separate LSTM modules.
+
+These two vectors are then concatenated, and a fully connected network is trained on top of the concatenated representations.
+
+<img src="http://keras.io/img/dual_lstm.png" alt="Dual LSTM" style="width: 600px;"/>
+
+```python
+from keras.models import Sequential
+from keras.layers import Merge, LSTM, Dense
+import numpy as np
+
+data_dim = 16
+timesteps = 8
+nb_classes = 10
+
+encoder_a = Sequential()
+encoder_a.add(LSTM(32, input_shape=(timesteps, data_dim)))
+
+encoder_b = Sequential()
+encoder_b.add(LSTM(32, input_shape=(timesteps, data_dim)))
+
+decoder = Sequential()
+decoder.add(Merge([encoder_a, encoder_b], mode='concat'))
+decoder.add(Dense(32, activation='relu'))
+decoder.add(Dense(nb_classes, activation='softmax'))
+
+decoder.compile(loss='categorical_crossentropy',
+                optimizer='rmsprop',
+                metrics=['accuracy'])
+
+# generate dummy training data
+x_train_a = np.random.random((1000, timesteps, data_dim))
+x_train_b = np.random.random((1000, timesteps, data_dim))
+y_train = np.random.random((1000, nb_classes))
+
+# generate dummy validation data
+x_val_a = np.random.random((100, timesteps, data_dim))
+x_val_b = np.random.random((100, timesteps, data_dim))
+y_val = np.random.random((100, nb_classes))
+
+decoder.fit([x_train_a, x_train_b], y_train,
+            batch_size=64, nb_epoch=5,
+            validation_data=([x_val_a, x_val_b], y_val))
+```

docs/templates/index.md

@@ -33,11 +33,12 @@ Keras is compatible with: __Python 2.7-3.5__.
 ------------------
 
 
+
 ## Getting started: 30 seconds to Keras
 
-The core datastructure of Keras is a __model__, a way to organize layers. There are two types of models: [`Sequential`](http://keras.io/models/#sequential) and [`Graph`](http://keras.io/models/#graph).
+The core data structure of Keras is a __model__, a way to organize layers. The main type of model is the [`Sequential`](http://keras.io/getting-started/sequential-model-guide) model, a linear stack of layers. For more complex architectures, you should use the [Keras function API](http://keras.io/getting-started/functional-api-guide).
 
-Here's the `Sequential` model (a linear pile of layers):
+Here's the `Sequential` model:
 
 ```python
 from keras.models import Sequential
@@ -50,15 +51,15 @@ Stacking layers is as easy as `.add()`:
 ```python
 from keras.layers.core import Dense, Activation
 
-model.add(Dense(output_dim=64, input_dim=100, init="glorot_uniform"))
+model.add(Dense(output_dim=64, input_dim=100))
 model.add(Activation("relu"))
-model.add(Dense(output_dim=10, init="glorot_uniform"))
+model.add(Dense(output_dim=10))
 model.add(Activation("softmax"))
 ```
 
 Once your model looks good, configure its learning process with `.compile()`:
 ```python
-model.compile(loss='categorical_crossentropy', optimizer='sgd')
+model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
 ```
 
 If you need to, you can further configure your optimizer. A core principle of Keras is to make things reasonably simple, while allowing the user to be fully in control when they need to (the ultimate control being the easy extensibility of the source code).
@@ -79,7 +80,7 @@ model.train_on_batch(X_batch, Y_batch)
 
 Evaluate your performance in one line:
 ```python
-objective_score = model.evaluate(X_test, Y_test, batch_size=32)
+loss_and_metrics = model.evaluate(X_test, Y_test, batch_size=32)
 ```
 
 Or generate predictions on new data:
@@ -88,12 +89,14 @@ classes = model.predict_classes(X_test, batch_size=32)
 proba = model.predict_proba(X_test, batch_size=32)
 ```
 
-Building a network of LSTMs, a deep CNN, a Neural Turing Machine, a word2vec embedder or any other model is just as fast. The ideas behind deep learning are simple, so why should their implementation be painful?
+Building a question answering system, an image classification model, a Neural Turing Machine, a word2vec embedder or any other model is just as fast. The ideas behind deep learning are simple, so why should their implementation be painful?
 
-Have a look at these [starter examples](http://keras.io/examples/).
+For a more in-depth tutorial about Keras, you can check out:
 
-In the [examples folder](https://github.com/fchollet/keras/tree/master/examples) of the repo, you will find more advanced models: question-answering with memory networks, text generation with stacked LSTMs, neural turing machines, etc.
+- [Getting started with the Sequential model](http://keras.io/getting-started/sequential-model-guide)
+- [Getting started with the functional API](http://keras.io/getting-started/functional-api-guide)
 
+In the [examples folder](https://github.com/fchollet/keras/tree/master/examples) of the repository, you will find more advanced models: question-answering with memory networks, text generation with stacked LSTMs, etc.
 
 ------------------
 
@@ -112,11 +115,6 @@ Keras uses the following dependencies:
 - Theano
     - [See installation instructions](http://deeplearning.net/software/theano/install.html#install).
 
-**Note**: You should use the latest version of Theano, not the PyPI version. Install it with:
-```
-sudo pip install git+git://github.com/Theano/Theano.git
-```
-
 *When using the TensorFlow backend:*
 
 - TensorFlow

docs/templates/layers/about-keras-layers.md

@@ -0,0 +1,27 @@
+# About Keras layers
+
+All Keras layers have a number of methods in common:
+
+- `layer.get_weights()`: returns the weights of the layer as a list of Numpy arrays.
+- `layer.set_weights(weights)`: sets the weights of the layer from a list of Numpy arrays (with the same shapes as the output of `get_weights`).
+- `layer.get_config()`: returns a dictionary containing the configuration of the layer. The layer can be reinstantiated from its config via:
+```python
+from keras.utils.layer_utils import layer_from_config
+
+config = layer.get_config()
+layer = layer_from_config(config)
+```
+
+If a layer has a single node (i.e. if it isn't a shared layer), you can get its input tensor, output tensor, input shape and output shape via:
+
+- `layer.input`
+- `layer.output`
+- `layer.input_shape`
+- `layer.output_shape`
+
+If the layer has multiple nodes (see: [the concept of layer node and shared layers](/getting-started/functional-api-guide/#the-concept-of-layer-node)), you can use the following methods:
+
+- `layer.get_input_at(node_index)`
+- `layer.get_output_at(node_index)`
+- `layer.get_input_shape_at(node_index)`
+- `layer.get_output_shape_at(node_index)`

docs/templates/layers/writing-your-own-keras-layers.md

@@ -0,0 +1,34 @@
+# Writing your own Keras layers
+
+For simple, stateless custom operations, you are probably better off using `layers.core.Lambda` layers. But for any custom operation that has trainable weights, you should implement your own layer.
+
+Here is the skeleton of a Keras layer. There are only three methods you need to implement:
+
+- `build(input_shape)`: this is where you will define your weights. Trainable weights should be added to the list `self.trainable_weights`. Other attributes of note are: `self.non_trainable_weights` (list) and `self.updates` (list of update tuples (tensor, new_tensor)). For an example of how to use `non_trainable_weights` and `updates`, see the code for the `BatchNormalization` layer.
+- `call(x)`: this is where the layer's logic lives. Unless you want you want your layer to support masking, you only have to care about the first argument passed to `call`: the input tensor.
+- `get_output_shape_for(input_shape)`: in case your layer modifies the shape of its input, you should specify here the shape transformation logic. This allows Keras to do automatic shape inference.
+
+```python
+from keras import backend as K
+from keras.engine.topology import Layer
+import numpy as np
+
+class MyLayer(Layer):
+    def __init__(self, output_dim, **kwargs):
+        self.output_dim = output_dim
+        super(MyLayer, self).__init__(**kwargs)
+
+    def build(self, input_shape):
+        input_dim = input_shape[1]
+        initial_weight_value = np.random.random((input_dim, output_dim))
+        self.W = K.variable(initial_weight_value)
+        self.trainable_weights = [self.W]
+
+    def call(self, x, mask=None):
+        return K.dot(x, self.W)
+
+    def get_output_shape_for(self, input_shape):
+        return (input_shape[0], self.output_dim)
+```
+
+The existing Keras layers provide ample examples of how to implement almost anything. Never hesitate to read the source code!

docs/templates/models.md

@@ -1,114 +0,0 @@
-Keras has two models: __Sequential__, a linear stack of layers, and __Graph__, a directed acyclic graph of layers.
-
-# Using the Sequential model
-
-```python
-from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation
-from keras.optimizers import SGD
-
-model = Sequential()
-model.add(Dense(2, init='uniform', input_dim=64))
-model.add(Activation('softmax'))
-
-model.compile(optimizer='sgd', loss='mse')
-
-'''
-Train the model for 3 epochs, in batches of 16 samples,
-on data stored in the Numpy array X_train,
-and labels stored in the Numpy array y_train:
-'''
-model.fit(X_train, y_train, nb_epoch=3, batch_size=16, verbose=1)
-'''
-What you will see with mode verbose=1:
-Train on 37800 samples, validate on 4200 samples
-Epoch 0
-37800/37800 [==============================] - 7s - loss: 0.0385
-Epoch 1
-37800/37800 [==============================] - 8s - loss: 0.0140
-Epoch 2
-10960/37800 [=======>......................] - ETA: 4s - loss: 0.0109
-'''
-
-model.fit(X_train, y_train, nb_epoch=3, batch_size=16, verbose=2)
-'''
-What you will see with mode verbose=2:
-Train on 37800 samples, validate on 4200 samples
-Epoch 0
-loss: 0.0190
-Epoch 1
-loss: 0.0146
-Epoch 2
-loss: 0.0049
-'''
-
-'''
-Demonstration of the show_accuracy argument
-'''
-model.fit(X_train, y_train, nb_epoch=3, batch_size=16, verbose=2, show_accuracy=True)
-'''
-Train on 37800 samples, validate on 4200 samples
-Epoch 0
-loss: 0.0190 - acc.: 0.8750
-Epoch 1
-loss: 0.0146 - acc.: 0.8750
-Epoch 2
-loss: 0.0049 - acc.: 1.0000
-'''
-
-'''
-Demonstration of the validation_split argument
-'''
-model.fit(X_train, y_train, nb_epoch=3, batch_size=16,
-          validation_split=0.1, show_accuracy=True, verbose=1)
-'''
-Train on 37800 samples, validate on 4200 samples
-Epoch 0
-37800/37800 [==============================] - 7s - loss: 0.0385 - acc.: 0.7258 - val. loss: 0.0160 - val. acc.: 0.9136
-Epoch 1
-37800/37800 [==============================] - 8s - loss: 0.0140 - acc.: 0.9265 - val. loss: 0.0109 - val. acc.: 0.9383
-Epoch 2
-10960/37800 [=======>......................] - ETA: 4s - loss: 0.0109 - acc.: 0.9420
-'''
-```
-
-# Using the Graph model
-
-```python
-# graph model with one input and two outputs
-graph = Graph()
-graph.add_input(name='input', input_shape=(32,))
-graph.add_node(Dense(16), name='dense1', input='input')
-graph.add_node(Dense(4), name='dense2', input='input')
-graph.add_node(Dense(4), name='dense3', input='dense1')
-graph.add_output(name='output1', input='dense2')
-graph.add_output(name='output2', input='dense3')
-
-graph.compile(optimizer='rmsprop', loss={'output1':'mse', 'output2':'mse'})
-history = graph.fit({'input':X_train, 'output1':y_train, 'output2':y2_train}, nb_epoch=10)
-
-```
-
-```python
-# graph model with two inputs and one output
-graph = Graph()
-graph.add_input(name='input1', input_shape=(32,))
-graph.add_input(name='input2', input_shape=(32,))
-graph.add_node(Dense(16), name='dense1', input='input1')
-graph.add_node(Dense(4), name='dense2', input='input2')
-graph.add_node(Dense(4), name='dense3', input='dense1')
-graph.add_output(name='output', inputs=['dense2', 'dense3'], merge_mode='sum')
-graph.compile(optimizer='rmsprop', loss={'output':'mse'})
-
-history = graph.fit({'input1':X_train, 'input2':X2_train, 'output':y_train}, nb_epoch=10)
-predictions = graph.predict({'input1':X_test, 'input2':X2_test}) # {'output':...}
-
-```
-
-----
-
-# Model API documentation
-
-
-
-{{autogenerated}}

docs/templates/models/about-keras-models.md

@@ -0,0 +1,33 @@
+# About Keras models
+
+There are two types of models available in Keras: [the Sequential model](/models/sequential) and [the Model class used with functional API](/models/model).
+
+These models have a number of methods in common:
+
+- `model.summary()`: prints a summary representation of your model.
+- `model.get_config()`: returns a dictionary containing the configuration of the model. The model can be reinstantiated from its config via:
+```python
+config = model.get_config()
+model = Model.from_config(config)
+# or, for Sequential:
+model = Sequential.from_config(config)
+```
+
+- `model.get_weights()`: returns a list of all weight tensors in the model, as Numpy arrays.
+- `model.set_weights(weights)`: sets the values of the weights of the model, from a list of Numpy arrays. The arrays in the list should have the same shape as those returned by `get_weights()`.
+- `model.to_json()`: returns a representation of the model as a JSON string. Note that the representation does not include the weights, only the architecture. You can reinstantiate the same model (with reinitialized weights) from the JSON string via:
+```python
+from models import model_from_json
+
+json_string = model.to_json()
+model = model_from_json(json_string)
+```
+- `model.to_yaml()`: returns a representation of the model as a YAML string. Note that the representation does not include the weights, only the architecture. You can reinstantiate the same model (with reinitialized weights) from the YAML string via:
+```python
+from models import model_from_yaml
+
+yaml_string = model.to_yaml()
+model = model_from_yaml(yaml_string)
+```
+- `model.save_weights(filepath)`: saves the weights of the model as a HDF5 file.
+- `model.load_weights(filepath)`: loads the weights of the model from a HDF5 file (created by `save_weights`).

docs/templates/models/model.md

@@ -0,0 +1,32 @@
+# Model class API
+
+In the functional API, given an input tensor and output tensor, you can instantiate a `Model` via:
+
+```python
+from keras.models import Model
+from keras.layers import Input, Dense
+
+a = Input(shape=(32,))
+b = Dense(32)(a)
+model = Model(input=a, output=b)
+```
+
+This model will include all layers required in the computation of `b` given `a`.
+
+In the case of multi-input or multi-output models, you can use lists as well:
+
+```python
+model = Model(input=[a1, a2], output=[b1, b3, b3])
+```
+
+For a detailed introduction of what `Model` can do, read [this guide to the Keras functional API](/getting-started/functional-api-guide).
+
+## Useful attributes of Model
+
+- `model.layers` is a flattened list of the layers comprising the model graph.
+- `model.inputs` is the list of input tensors.
+- `model.outputs` is the list of output tensors.
+
+## Methods
+
+{{autogenerated}}

docs/templates/models/sequential.md

@@ -0,0 +1,14 @@
+# The Sequential model API
+
+To get started, read [this guide to the Keras Sequential model](/getting-started/sequential-model-guide).
+
+## Useful attributes of Model
+
+- `model.layers` is a list of the layers added to the model.
+
+
+----
+
+## Sequential model methods
+
+{{autogenerated}}

docs/templates/objectives.md

@@ -7,10 +7,10 @@ An objective function (or loss function, or optimization score function) is one
 model.compile(loss='mean_squared_error', optimizer='sgd')
 ```
 
-You can either pass the name of an existing objective, or pass a Theano symbolic function that returns a scalar for each data-point and takes the following two arguments:
+You can either pass the name of an existing objective, or pass a Theano/TensorFlow symbolic function that returns a scalar for each data-point and takes the following two arguments:
 
-- __y_true__: True labels. Theano tensor.
-- __y_pred__: Predictions. Theano tensor of the same shape as y_true.
+- __y_true__: True labels. Theano/TensorFlow tensor.
+- __y_pred__: Predictions. Theano/TensorFlow tensor of the same shape as y_true.
 
 The actual optimized objective is the mean of the output array across all datapoints.
 
@@ -26,5 +26,6 @@ For a few examples of such functions, check out the [objectives source](https://
 - __hinge__
 - __binary_crossentropy__: Also known as logloss. 
 - __categorical_crossentropy__: Also known as multiclass logloss. __Note__: using this objective requires that your labels are binary arrays of shape `(nb_samples, nb_classes)`.
+- __sparse_categorical_crossentropy__: As above but accepts sparse labels. __Note__: this objective still requires that your labels have the same number of dimensions as your outputs; you may need to add a length-1 dimension to the shape of your labels, e.g with `np.expand_dims(y, -1)`.
 - __poisson__: mean of `(predictions - targets * log(predictions))`
 - __cosine_proximity__: the opposite (negative) of the mean cosine proximity between predictions and targets.

docs/templates/preprocessing/image.md

@@ -11,8 +11,13 @@ keras.preprocessing.image.ImageDataGenerator(featurewise_center=True,
     width_shift_range=0.,
     height_shift_range=0.,
     shear_range=0.,
+    zoom_range=0.,
+    channel_shift_range=0.,
+    fill_mode='nearest',
+    cval=0.,
     horizontal_flip=False,
-    vertical_flip=False)
+    vertical_flip=False,
+    dim_ordering='th')
 ```
 
 Generate batches of tensor image data with real-time data augmentation. The data will be looped over (in batches) indefinitely.
@@ -27,8 +32,15 @@ Generate batches of tensor image data with real-time data augmentation. The data
     - __width_shift_range__: Float (fraction of total width). Range for random horizontal shifts.
     - __height_shift_range__: Float (fraction of total height). Range for random vertical shifts.
     - __shear_range__: Float. Shear Intensity (Shear angle in counter-clockwise direction as radians)
+    - __zoom_range__: Float or [lower, upper]. Range for random zoom. If a float, `[lower, upper] = [1-zoom_range, 1+zoom_range]`.
+    - __channel_shift_range__: Float. Range for random channel shifts.
+    - __fill_mode__: One of {"constant", "nearest", "reflect" or "wrap"}.  Points outside the boundaries of the input are filled according to the given mode.
+    - __cval__: Float or Int. Value used for points outside the boundaries when `fill_mode = "constant"`.
     - __horizontal_flip__: Boolean. Randomly flip inputs horizontally.
     - __vertical_flip__: Boolean. Randomly flip inputs vertically.
+    - __dim_ordering__: One of {"th", "tf"}.
+        "tf" mode means that the images should have shape `(samples, width, height, channels)`,
+        "th" mode means that the images should have shape `(samples, channels, width, height)`.
 
 - __Methods__:
     - __fit(X)__: Required if featurewise_center or featurewise_std_normalization or zca_whitening. Compute necessary quantities on some sample data.

docs/templates/scikit-learn-api.md

@@ -0,0 +1,45 @@
+# Wrappers for the Sciki-Learn API
+
+You can use `Sequential` Keras models (single-input only) as part of your Scikit-Learn workflow via the wrappers found at `keras.wrappers.sklearn.py`.
+
+There are two wrappers available:
+
+`keras.wrappers.sklearn.KerasClassifier(build_fn=None, **sk_params)`, which implements the sklearn classifier interface,
+
+`keras.wrappers.sklearn.KerasRegressor(build_fn=None, **sk_params)`, which implements the sklearn regressor interface.
+
+### Arguments
+
+- __build_fn__: callable function or class instance
+- __sk_params__: model parameters & fitting parameters
+
+`build_fn` should construct, compile and return a Keras model, which
+will then be used to fit/predict. One of the following
+three values could be passed to build_fn:
+
+1. A function
+2. An instance of a class that implements the __call__ method
+3. None. This means you implement a class that inherits from either
+`KerasClassifier` or `KerasRegressor`. The __call__ method of the
+present class will then be treated as the default build_fn.
+
+`sk_params` takes both model parameters and fitting parameters. Legal model
+parameters are the arguments of `build_fn`. Note that like all other
+estimators in scikit-learn, 'build_fn' should provide defalult values for
+its arguments, so that you could create the estimator without passing any
+values to `sk_params`.
+
+`sk_params` could also accept parameters for calling `fit`, `predict`,
+`predict_proba`, and `score` methods (e.g., `nb_epoch`, `batch_size`).
+fitting (predicting) parameters are selected in the following order:
+
+1. Values passed to the dictionary arguments of
+`fit`, `predict`, `predict_proba`, and `score` methods
+2. Values passed to `sk_params`
+3. The default values of the `keras.models.Sequential`
+`fit`, `predict`, `predict_proba` and `score` methods
+
+When using scikit-learn's `grid_search` API, legal tunable parameters are
+those you could pass to `sk_params`, including fitting parameters.
+In other words, you could use `grid_search` to search for the best
+`batch_size` or `nb_epoch` as well as the model parameters.

docs/templates/visualization.md

@@ -10,11 +10,15 @@ from keras.utils.visualize_util import plot
 plot(model, to_file='model.png')
 ```
 
+`plot` takes one optional arguments:
+
+- `show_shapes` (defaults to False) controls whether output shapes are shown in the graph.
+
 You can also directly obtain the `pydot.Graph` object and render it yourself,
 for example to show it in an ipython notebook :
 ```python
 from IPython.display import SVG
-from keras.utils.visualize_util import to_graph
+from keras.utils.visualize_util import model_to_dot
 
-SVG(to_graph(model).create(prog='dot', format='svg'))
+SVG(model_to_dot(model).create(prog='dot', format='svg'))
 ```

examples/addition_rnn.py

@@ -27,9 +27,9 @@ Five digits inverted:
 '''
 
 from __future__ import print_function
-from keras.models import Sequential, slice_X
-from keras.layers.core import Activation, TimeDistributedDense, RepeatVector
-from keras.layers import recurrent
+from keras.models import Sequential
+from keras.engine.training import slice_X
+from keras.layers import Activation, TimeDistributedDense, RepeatVector, recurrent
 import numpy as np
 from six.moves import range
 
@@ -142,7 +142,9 @@ for _ in range(LAYERS):
 model.add(TimeDistributedDense(len(chars)))
 model.add(Activation('softmax'))
 
-model.compile(loss='categorical_crossentropy', optimizer='adam')
+model.compile(loss='categorical_crossentropy',
+              optimizer='adam',
+              metrics=['accuracy'])
 
 # Train the model each generation and show predictions against the validation dataset
 for iteration in range(1, 200):
@@ -150,7 +152,7 @@ for iteration in range(1, 200):
     print('-' * 50)
     print('Iteration', iteration)
     model.fit(X_train, y_train, batch_size=BATCH_SIZE, nb_epoch=1,
-              validation_data=(X_val, y_val), show_accuracy=True)
+              validation_data=(X_val, y_val))
     ###
     # Select 10 samples from the validation set at random so we can visualize errors
     for i in range(10):

examples/antirectifier.py

@@ -2,7 +2,7 @@
 
 We build a custom activation layer called 'Antirectifier',
 which modifies the shape of the tensor that passes through it.
-We need to specify two methods: `output_shape` and `get_output`.
+We need to specify two methods: `get_output_shape_for` and `call`.
 
 Note that the same result can also be achieved via a Lambda layer.
 
@@ -11,9 +11,8 @@ backend (`K`), our code can run both on TensorFlow and Theano.
 '''
 
 from __future__ import print_function
-import numpy as np
 from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Layer, Activation
+from keras.layers import Dense, Dropout, Layer, Activation
 from keras.datasets import mnist
 from keras import backend as K
 from keras.utils import np_utils
@@ -46,15 +45,13 @@ class Antirectifier(Layer):
         with twice less parameters yet with comparable
         classification accuracy as an equivalent ReLU-based network.
     '''
-    @property
-    def output_shape(self):
-        shape = list(self.input_shape)
+    def get_output_shape_for(self, input_shape):
+        shape = list(input_shape)
         assert len(shape) == 2  # only valid for 2D tensors
         shape[-1] *= 2
         return tuple(shape)
 
-    def get_output(self, train):
-        x = self.get_input(train)
+    def call(self, x, mask=None):
         x -= K.mean(x, axis=1, keepdims=True)
         x = K.l2_normalize(x, axis=1)
         pos = K.relu(x)
@@ -66,7 +63,7 @@ batch_size = 128
 nb_classes = 10
 nb_epoch = 40
 
-# the data, shuffled and split between tran and test sets
+# the data, shuffled and split between train and test sets
 (X_train, y_train), (X_test, y_test) = mnist.load_data()
 
 X_train = X_train.reshape(60000, 784)
@@ -94,13 +91,14 @@ model.add(Dense(10))
 model.add(Activation('softmax'))
 
 # compile the model
-model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
+model.compile(loss='categorical_crossentropy',
+              optimizer='rmsprop',
+              metrics=['accuracy'])
 
 # train the model
 model.fit(X_train, Y_train,
           batch_size=batch_size, nb_epoch=nb_epoch,
-          show_accuracy=True, verbose=1,
-          validation_data=(X_test, Y_test))
+          verbose=1, validation_data=(X_test, Y_test))
 
 # next, compare with an equivalent network
 # with2x bigger Dense layers and ReLU

examples/babi_memnn.py

@@ -1,4 +1,4 @@
-'''Train a memory network on the bAbI dataset.
+'''Trains a memory network on the bAbI dataset.
 
 References:
 - Jason Weston, Antoine Bordes, Sumit Chopra, Tomas Mikolov, Alexander M. Rush,
@@ -16,9 +16,9 @@ Time per epoch: 3s on CPU (core i7).
 from __future__ import print_function
 from keras.models import Sequential
 from keras.layers.embeddings import Embedding
-from keras.layers.core import Activation, Dense, Merge, Permute, Dropout
-from keras.layers.recurrent import LSTM
-from keras.datasets.data_utils import get_file
+from keras.layers import Activation, Dense, Merge, Permute, Dropout
+from keras.layers import LSTM
+from keras.utils.data_utils import get_file
 from keras.preprocessing.sequence import pad_sequences
 from functools import reduce
 import tarfile
@@ -167,7 +167,7 @@ question_encoder.add(Dropout(0.3))
 match = Sequential()
 match.add(Merge([input_encoder_m, question_encoder],
                 mode='dot',
-                dot_axes=[(2,), (2,)]))
+                dot_axes=[2, 2]))
 # output: (samples, story_maxlen, query_maxlen)
 # embed the input into a single vector with size = story_maxlen:
 input_encoder_c = Sequential()
@@ -195,10 +195,10 @@ answer.add(Dense(vocab_size))
 # we output a probability distribution over the vocabulary
 answer.add(Activation('softmax'))
 
-answer.compile(optimizer='rmsprop', loss='categorical_crossentropy')
+answer.compile(optimizer='rmsprop', loss='categorical_crossentropy',
+               metrics=['accuracy'])
 # Note: you could use a Graph model to avoid repeat the input twice
 answer.fit([inputs_train, queries_train, inputs_train], answers_train,
            batch_size=32,
            nb_epoch=120,
-           show_accuracy=True,
            validation_data=([inputs_test, queries_test, inputs_test], answers_test))

examples/babi_rnn.py

@@ -7,8 +7,8 @@ http://arxiv.org/abs/1502.05698
 
 Task Number                  | FB LSTM Baseline | Keras QA
 ---                          | ---              | ---
-QA1 - Single Supporting Fact | 50               | 52.1
-QA2 - Two Supporting Facts   | 20               | 37.0
+QA1 - Single Supporting Fact | 50               | 100.0
+QA2 - Two Supporting Facts   | 20               | 50.0
 QA3 - Three Supporting Facts | 20               | 20.5
 QA4 - Two Arg. Relations     | 61               | 62.9
 QA5 - Three Arg. Relations   | 70               | 61.9
@@ -34,8 +34,8 @@ https://research.facebook.com/researchers/1543934539189348
 Notes:
 
 - With default word, sentence, and query vector sizes, the GRU model achieves:
-  - 52.1% test accuracy on QA1 in 20 epochs (2 seconds per epoch on CPU)
-  - 37.0% test accuracy on QA2 in 20 epochs (16 seconds per epoch on CPU)
+  - 100% test accuracy on QA1 in 20 epochs (2 seconds per epoch on CPU)
+  - 50% test accuracy on QA2 in 20 epochs (16 seconds per epoch on CPU)
 In comparison, the Facebook paper achieves 50% and 20% for the LSTM baseline.
 
 - The task does not traditionally parse the question separately. This likely
@@ -64,9 +64,9 @@ import tarfile
 import numpy as np
 np.random.seed(1337)  # for reproducibility
 
-from keras.datasets.data_utils import get_file
+from keras.utils.data_utils import get_file
 from keras.layers.embeddings import Embedding
-from keras.layers.core import Dense, Merge
+from keras.layers import Dense, Merge, Dropout, RepeatVector
 from keras.layers import recurrent
 from keras.models import Sequential
 from keras.preprocessing.sequence import pad_sequences
@@ -138,12 +138,12 @@ def vectorize_stories(data, word_idx, story_maxlen, query_maxlen):
         Y.append(y)
     return pad_sequences(X, maxlen=story_maxlen), pad_sequences(Xq, maxlen=query_maxlen), np.array(Y)
 
-RNN = recurrent.GRU
+RNN = recurrent.LSTM
 EMBED_HIDDEN_SIZE = 50
 SENT_HIDDEN_SIZE = 100
 QUERY_HIDDEN_SIZE = 100
 BATCH_SIZE = 32
-EPOCHS = 20
+EPOCHS = 40
 print('RNN / Embed / Sent / Query = {}, {}, {}, {}'.format(RNN, EMBED_HIDDEN_SIZE, SENT_HIDDEN_SIZE, QUERY_HIDDEN_SIZE))
 
 path = get_file('babi-tasks-v1-2.tar.gz', origin='http://www.thespermwhale.com/jaseweston/babi/tasks_1-20_v1-2.tar.gz')
@@ -178,20 +178,28 @@ print('story_maxlen, query_maxlen = {}, {}'.format(story_maxlen, query_maxlen))
 print('Build model...')
 
 sentrnn = Sequential()
-sentrnn.add(Embedding(vocab_size, EMBED_HIDDEN_SIZE, mask_zero=True))
-sentrnn.add(RNN(SENT_HIDDEN_SIZE, return_sequences=False))
+sentrnn.add(Embedding(vocab_size, EMBED_HIDDEN_SIZE,
+                      input_length=story_maxlen))
+sentrnn.add(Dropout(0.3))
 
 qrnn = Sequential()
-qrnn.add(Embedding(vocab_size, EMBED_HIDDEN_SIZE))
-qrnn.add(RNN(QUERY_HIDDEN_SIZE, return_sequences=False))
+qrnn.add(Embedding(vocab_size, EMBED_HIDDEN_SIZE,
+                   input_length=query_maxlen))
+qrnn.add(Dropout(0.3))
+qrnn.add(RNN(EMBED_HIDDEN_SIZE, return_sequences=False))
+qrnn.add(RepeatVector(story_maxlen))
 
 model = Sequential()
-model.add(Merge([sentrnn, qrnn], mode='concat'))
+model.add(Merge([sentrnn, qrnn], mode='sum'))
+model.add(RNN(EMBED_HIDDEN_SIZE, return_sequences=False))
+model.add(Dropout(0.3))
 model.add(Dense(vocab_size, activation='softmax'))
 
-model.compile(optimizer='adam', loss='categorical_crossentropy', class_mode='categorical')
+model.compile(optimizer='adam',
+              loss='categorical_crossentropy',
+              metrics=['accuracy'])
 
 print('Training')
-model.fit([X, Xq], Y, batch_size=BATCH_SIZE, nb_epoch=EPOCHS, validation_split=0.05, show_accuracy=True)
-loss, acc = model.evaluate([tX, tXq], tY, batch_size=BATCH_SIZE, show_accuracy=True)
+model.fit([X, Xq], Y, batch_size=BATCH_SIZE, nb_epoch=EPOCHS, validation_split=0.05)
+loss, acc = model.evaluate([tX, tXq], tY, batch_size=BATCH_SIZE)
 print('Test loss / test accuracy = {:.4f} / {:.4f}'.format(loss, acc))

examples/cifar10_cnn.py

@@ -15,8 +15,8 @@ from __future__ import print_function
 from keras.datasets import cifar10
 from keras.preprocessing.image import ImageDataGenerator
 from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation, Flatten
-from keras.layers.convolutional import Convolution2D, MaxPooling2D
+from keras.layers import Dense, Dropout, Activation, Flatten
+from keras.layers import Convolution2D, MaxPooling2D
 from keras.optimizers import SGD
 from keras.utils import np_utils
 
@@ -66,7 +66,9 @@ model.add(Activation('softmax'))
 
 # let's train the model using SGD + momentum (how original).
 sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
-model.compile(loss='categorical_crossentropy', optimizer=sgd)
+model.compile(loss='categorical_crossentropy',
+              optimizer=sgd,
+              metrics=['accuracy'])
 
 X_train = X_train.astype('float32')
 X_test = X_test.astype('float32')
@@ -75,9 +77,11 @@ X_test /= 255
 
 if not data_augmentation:
     print('Not using data augmentation.')
-    model.fit(X_train, Y_train, batch_size=batch_size,
-              nb_epoch=nb_epoch, show_accuracy=True,
-              validation_data=(X_test, Y_test), shuffle=True)
+    model.fit(X_train, Y_train,
+              batch_size=batch_size,
+              nb_epoch=nb_epoch,
+              validation_data=(X_test, Y_test),
+              shuffle=True)
 else:
     print('Using real-time data augmentation.')
 
@@ -99,8 +103,8 @@ else:
     datagen.fit(X_train)
 
     # fit the model on the batches generated by datagen.flow()
-    model.fit_generator(datagen.flow(X_train, Y_train, batch_size=batch_size),
+    model.fit_generator(datagen.flow(X_train, Y_train,
+                        batch_size=batch_size),
                         samples_per_epoch=X_train.shape[0],
-                        nb_epoch=nb_epoch, show_accuracy=True,
-                        validation_data=(X_test, Y_test),
-                        nb_worker=1)
+                        nb_epoch=nb_epoch,
+                        validation_data=(X_test, Y_test))

examples/conv_filter_visualization.py

@@ -47,15 +47,13 @@ def deprocess_image(x):
     x = np.clip(x, 0, 255).astype('uint8')
     return x
 
-# this will contain our generated image
-input_img = K.placeholder((1, 3, img_width, img_height))
-
-# build the VGG16 network with our input_img as input
-first_layer = ZeroPadding2D((1, 1), input_shape=(3, img_width, img_height))
-first_layer.input = input_img
-
+# build the VGG16 network
 model = Sequential()
-model.add(first_layer)
+model.add(ZeroPadding2D((1, 1), batch_input_shape=(1, 3, img_width, img_height)))
+first_layer = model.layers[-1]
+# this is a placeholder tensor that will contain our generated images
+input_img = first_layer.input
+
 model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1'))
 model.add(ZeroPadding2D((1, 1)))
 model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2'))
@@ -125,7 +123,7 @@ for filter_index in range(0, 200):
 
     # we build a loss function that maximizes the activation
     # of the nth filter of the layer considered
-    layer_output = layer_dict[layer_name].get_output()
+    layer_output = layer_dict[layer_name].output
     loss = K.mean(layer_output[:, filter_index, :, :])
 
     # we compute the gradient of the input picture wrt this loss

examples/deep_dream.py

@@ -21,9 +21,10 @@ from scipy.optimize import fmin_l_bfgs_b
 import time
 import argparse
 import h5py
+import os
 
 from keras.models import Sequential
-from keras.layers.convolutional import Convolution2D, ZeroPadding2D, MaxPooling2D
+from keras.layers import Convolution2D, ZeroPadding2D, MaxPooling2D
 from keras import backend as K
 
 parser = argparse.ArgumentParser(description='Deep Dreams with Keras.')
@@ -73,15 +74,13 @@ def deprocess_image(x):
     x = np.clip(x, 0, 255).astype('uint8')
     return x
 
-# this will contain our generated image
-dream = K.placeholder((1, 3, img_width, img_height))
-
-# build the VGG16 network with our dream as input
-first_layer = ZeroPadding2D((1, 1), input_shape=(3, img_width, img_height))
-first_layer.input = dream
-
+# build the VGG16 network
 model = Sequential()
-model.add(first_layer)
+model.add(ZeroPadding2D((1, 1), batch_input_shape=(1, 3, img_width, img_height)))
+first_layer = model.layers[-1]
+# this is a placeholder tensor that will contain our generated images
+dream = first_layer.input
+
 model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1'))
 model.add(ZeroPadding2D((1, 1)))
 model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2'))
@@ -149,7 +148,7 @@ for layer_name in settings['features']:
     # add the L2 norm of the features of a layer to the loss
     assert layer_name in layer_dict.keys(), 'Layer ' + layer_name + ' not found in model.'
     coeff = settings['features'][layer_name]
-    x = layer_dict[layer_name].get_output()
+    x = layer_dict[layer_name].output
     shape = layer_dict[layer_name].output_shape
     # we avoid border artifacts by only involving non-border pixels in the loss
     loss -= coeff * K.sum(K.square(x[:, :, 2: shape[2]-2, 2: shape[3]-2])) / np.prod(shape[1:])

examples/imdb_bidirectional_lstm.py

@@ -1,8 +1,5 @@
 '''Train a Bidirectional LSTM on the IMDB sentiment classification task.
 
-GPU command:
-    THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_bidirectional_lstm.py
-
 Output after 4 epochs on CPU: ~0.8146
 Time per epoch on CPU (Core i7): ~150s.
 '''
@@ -12,11 +9,8 @@ import numpy as np
 np.random.seed(1337)  # for reproducibility
 
 from keras.preprocessing import sequence
-from keras.utils.np_utils import accuracy
-from keras.models import Graph
-from keras.layers.core import Dense, Dropout
-from keras.layers.embeddings import Embedding
-from keras.layers.recurrent import LSTM
+from keras.models import Model
+from keras.layers import Dense, Dropout, Embedding, LSTM, Input, merge
 from keras.datasets import imdb
 
 
@@ -38,25 +32,30 @@ print('X_test shape:', X_test.shape)
 y_train = np.array(y_train)
 y_test = np.array(y_test)
 
-print('Build model...')
-model = Graph()
-model.add_input(name='input', input_shape=(maxlen,), dtype=int)
-model.add_node(Embedding(max_features, 128, input_length=maxlen),
-               name='embedding', input='input')
-model.add_node(LSTM(64), name='forward', input='embedding')
-model.add_node(LSTM(64, go_backwards=True), name='backward', input='embedding')
-model.add_node(Dropout(0.5), name='dropout', inputs=['forward', 'backward'])
-model.add_node(Dense(1, activation='sigmoid'), name='sigmoid', input='dropout')
-model.add_output(name='output', input='sigmoid')
+
+# this is the placeholder tensor for the input sequences
+sequence = Input(shape=(maxlen,), dtype='int32')
+# this embedding layer will transform the sequences of integers
+# into vectors of size 128
+embedded = Embedding(max_features, 128, input_length=maxlen)(sequence)
+
+# apply forwards LSTM
+forwards = LSTM(64)(embedded)
+# apply backwards LSTM
+backwards = LSTM(64, go_backwards=True)(embedded)
+
+# concatenate the outputs of the 2 LSTMs
+merged = merge([forwards, backwards], mode='concat', concat_axis=-1)
+after_dp = Dropout(0.5)(merged)
+output = Dense(1, activation='sigmoid')(after_dp)
+
+model = Model(input=sequence, output=output)
 
 # try using different optimizers and different optimizer configs
-model.compile('adam', {'output': 'binary_crossentropy'})
+model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])
 
 print('Train...')
-model.fit({'input': X_train, 'output': y_train},
+model.fit(X_train, y_train,
           batch_size=batch_size,
-          nb_epoch=4)
-acc = accuracy(y_test,
-               np.round(np.array(model.predict({'input': X_test},
-                                               batch_size=batch_size)['output'])))
-print('Test accuracy:', acc)
+          nb_epoch=4,
+          validation_data=[X_test, y_test])

examples/imdb_cnn.py

@@ -1,8 +1,9 @@
 '''This example demonstrates the use of Convolution1D for text classification.
 
-Run on GPU: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_cnn.py
+Gets to 0.88 test accuracy after 2 epochs. 
+90s/epoch on Intel i5 2.4Ghz CPU.
+10s/epoch on Tesla K40 GPU.
 
-Get to 0.835 test accuracy after 2 epochs. 100s/epoch on K520 GPU.
 '''
 
 from __future__ import print_function
@@ -11,17 +12,18 @@ np.random.seed(1337)  # for reproducibility
 
 from keras.preprocessing import sequence
 from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation, Flatten
-from keras.layers.embeddings import Embedding
-from keras.layers.convolutional import Convolution1D, MaxPooling1D
+from keras.layers import Dense, Dropout, Activation, Lambda
+from keras.layers import Embedding
+from keras.layers import Convolution1D
 from keras.datasets import imdb
+from keras import backend as K
 
 
 # set parameters:
 max_features = 5000
-maxlen = 100
+maxlen = 400
 batch_size = 32
-embedding_dims = 100
+embedding_dims = 50
 nb_filter = 250
 filter_length = 3
 hidden_dims = 250
@@ -44,8 +46,10 @@ model = Sequential()
 
 # we start off with an efficient embedding layer which maps
 # our vocab indices into embedding_dims dimensions
-model.add(Embedding(max_features, embedding_dims, input_length=maxlen))
-model.add(Dropout(0.25))
+model.add(Embedding(max_features,
+                    embedding_dims,
+                    input_length=maxlen,
+                    dropout=0.2))
 
 # we add a Convolution1D, which will learn nb_filter
 # word group filters of size filter_length:
@@ -54,16 +58,17 @@ model.add(Convolution1D(nb_filter=nb_filter,
                         border_mode='valid',
                         activation='relu',
                         subsample_length=1))
-# we use standard max pooling (halving the output of the previous layer):
-model.add(MaxPooling1D(pool_length=2))
 
-# We flatten the output of the conv layer,
-# so that we can add a vanilla dense layer:
-model.add(Flatten())
+# we use max over time pooling by defining a python function to use
+# in a Lambda layer
+def max_1d(X):
+    return K.max(X, axis=1)
+
+model.add(Lambda(max_1d, output_shape=(nb_filter,)))
 
 # We add a vanilla hidden layer:
 model.add(Dense(hidden_dims))
-model.add(Dropout(0.25))
+model.add(Dropout(0.2))
 model.add(Activation('relu'))
 
 # We project onto a single unit output layer, and squash it with a sigmoid:
@@ -71,8 +76,9 @@ model.add(Dense(1))
 model.add(Activation('sigmoid'))
 
 model.compile(loss='binary_crossentropy',
-              optimizer='rmsprop',
-              class_mode='binary')
-model.fit(X_train, y_train, batch_size=batch_size,
-          nb_epoch=nb_epoch, show_accuracy=True,
+              optimizer='adam',
+              metrics=['accuracy'])
+model.fit(X_train, y_train,
+          batch_size=batch_size,
+          nb_epoch=nb_epoch,
           validation_data=(X_test, y_test))

examples/imdb_cnn_lstm.py

@@ -1,22 +1,18 @@
 '''Train a recurrent convolutional network on the IMDB sentiment
 classification task.
 
-GPU command:
-    THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_cnn_lstm.py
-
-Get to 0.8498 test accuracy after 2 epochs. 41s/epoch on K520 GPU.
+Gets to 0.8498 test accuracy after 2 epochs. 41s/epoch on K520 GPU.
 '''
-
 from __future__ import print_function
 import numpy as np
 np.random.seed(1337)  # for reproducibility
 
 from keras.preprocessing import sequence
 from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation
-from keras.layers.embeddings import Embedding
-from keras.layers.recurrent import LSTM, GRU, SimpleRNN
-from keras.layers.convolutional import Convolution1D, MaxPooling1D
+from keras.layers import Dense, Dropout, Activation
+from keras.layers import Embedding
+from keras.layers import LSTM, GRU, SimpleRNN
+from keras.layers import Convolution1D, MaxPooling1D
 from keras.datasets import imdb
 
 
@@ -71,12 +67,11 @@ model.add(Activation('sigmoid'))
 
 model.compile(loss='binary_crossentropy',
               optimizer='adam',
-              class_mode='binary')
+              metrics=['accuracy'])
 
 print('Train...')
 model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch,
-          validation_data=(X_test, y_test), show_accuracy=True)
-score, acc = model.evaluate(X_test, y_test, batch_size=batch_size,
-                            show_accuracy=True)
+          validation_data=(X_test, y_test))
+score, acc = model.evaluate(X_test, y_test, batch_size=batch_size)
 print('Test score:', score)
 print('Test accuracy:', acc)

examples/imdb_lstm.py

@@ -1,4 +1,4 @@
-'''Train a LSTM on the IMDB sentiment classification task.
+'''Trains a LSTM on the IMDB sentiment classification task.
 
 The dataset is actually too small for LSTM to be of any advantage
 compared to simpler, much faster methods such as TF-IDF+LogReg.
@@ -11,11 +11,7 @@ Some configurations won't converge.
 
 - LSTM loss decrease patterns during training can be quite different
 from what you see with CNNs/MLPs/etc.
-
-GPU command:
-    THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_lstm.py
 '''
-
 from __future__ import print_function
 import numpy as np
 np.random.seed(1337)  # for reproducibility
@@ -23,13 +19,12 @@ np.random.seed(1337)  # for reproducibility
 from keras.preprocessing import sequence
 from keras.utils import np_utils
 from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation
-from keras.layers.embeddings import Embedding
-from keras.layers.recurrent import LSTM
+from keras.layers import Dense, Dropout, Activation, Embedding
+from keras.layers import LSTM, SimpleRNN, GRU
 from keras.datasets import imdb
 
 max_features = 20000
-maxlen = 100  # cut texts after this number of words (among top max_features most common words)
+maxlen = 80  # cut texts after this number of words (among top max_features most common words)
 batch_size = 32
 
 print('Loading data...')
@@ -38,7 +33,7 @@ print('Loading data...')
 print(len(X_train), 'train sequences')
 print(len(X_test), 'test sequences')
 
-print("Pad sequences (samples x time)")
+print('Pad sequences (samples x time)')
 X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
 X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
 print('X_train shape:', X_train.shape)
@@ -46,22 +41,22 @@ print('X_test shape:', X_test.shape)
 
 print('Build model...')
 model = Sequential()
-model.add(Embedding(max_features, 128, input_length=maxlen))
-model.add(LSTM(128))  # try using a GRU instead, for fun
-model.add(Dropout(0.5))
+model.add(Embedding(max_features, 128, input_length=maxlen, dropout=0.2))
+model.add(LSTM(128, dropout_W=0.2, dropout_U=0.2))  # try using a GRU instead, for fun
 model.add(Dense(1))
 model.add(Activation('sigmoid'))
 
 # try using different optimizers and different optimizer configs
 model.compile(loss='binary_crossentropy',
               optimizer='adam',
-              class_mode="binary")
+              metrics=['accuracy'])
 
-print("Train...")
-model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=3,
-          validation_data=(X_test, y_test), show_accuracy=True)
+print('Train...')
+print(X_train.shape)
+print(y_train.shape)
+model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=15,
+          validation_data=(X_test, y_test))
 score, acc = model.evaluate(X_test, y_test,
-                            batch_size=batch_size,
-                            show_accuracy=True)
+                            batch_size=batch_size)
 print('Test score:', score)
 print('Test accuracy:', acc)

examples/inception_v3.py

@@ -0,0 +1,290 @@
+'''This script demonstrates how to build the Inception v3 architecture
+using the Keras functional API.
+We are not actually training it here, for lack of appropriate data.
+
+For more information about this architecture, see:
+
+"Rethinking the Inception Architecture for Computer Vision"
+Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna
+http://arxiv.org/abs/1512.00567
+'''
+from keras.layers import Convolution2D, MaxPooling2D, AveragePooling2D
+from keras.layers import BatchNormalization, Flatten, Dense, Dropout
+from keras.layers import Input, merge
+from keras.models import Model
+from keras import regularizers
+
+
+# global constants
+NB_CLASS = 1000  # number of classes
+DIM_ORDERING = 'th'  # 'th' (channels, width, height) or 'tf' (width, height, channels)
+WEIGHT_DECAY = 0.  # L2 regularization factor
+USE_BN = False  # whether to use batch normalization
+
+
+def conv2D_bn(x, nb_filter, nb_row, nb_col,
+              border_mode='same', subsample=(1, 1),
+              activation='relu', batch_norm=USE_BN,
+              weight_decay=WEIGHT_DECAY, dim_ordering=DIM_ORDERING):
+    '''Utility function to apply to a tensor a module conv + BN
+    with optional weight decay (L2 weight regularization).
+    '''
+    if weight_decay:
+        W_regularizer = regularizers.l2(weight_decay)
+        b_regularizer = regularizers.l2(weight_decay)
+    else:
+        W_regularizer = None
+        b_regularizer = None
+    x = Convolution2D(nb_filter, nb_row, nb_col,
+                      subsample=subsample,
+                      activation=activation,
+                      border_mode=border_mode,
+                      W_regularizer=W_regularizer,
+                      b_regularizer=b_regularizer,
+                      dim_ordering=dim_ordering)(x)
+    if batch_norm:
+        x = BatchNormalization()(x)
+    return x
+
+# Define image input layer
+
+if DIM_ORDERING == 'th':
+    img_input = Input(shape=(3, 299, 299))
+    CONCAT_AXIS = 1
+elif DIM_ORDERING == 'tf':
+    img_input = Input(shape=(299, 299, 3))
+    CONCAT_AXIS = 3
+else:
+    raise Exception('Invalid dim ordering: ' + str(DIM_ORDERING))
+
+# Entry module
+
+x = conv2D_bn(img_input, 32, 3, 3, subsample=(2, 2), border_mode='valid')
+x = conv2D_bn(x, 32, 3, 3, border_mode='valid')
+x = conv2D_bn(x, 64, 3, 3)
+x = MaxPooling2D((3, 3), strides=(2, 2), dim_ordering=DIM_ORDERING)(x)
+
+x = conv2D_bn(x, 80, 1, 1, border_mode='valid')
+x = conv2D_bn(x, 192, 3, 3, border_mode='valid')
+x = MaxPooling2D((3, 3), strides=(2, 2), dim_ordering=DIM_ORDERING)(x)
+
+# mixed: 35 x 35 x 256
+
+branch1x1 = conv2D_bn(x, 64, 1, 1)
+
+branch5x5 = conv2D_bn(x, 48, 1, 1)
+branch5x5 = conv2D_bn(branch5x5, 64, 5, 5)
+
+branch3x3dbl = conv2D_bn(x, 64, 1, 1)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 32, 1, 1)
+x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed_1: 35 x 35 x 288
+
+branch1x1 = conv2D_bn(x, 64, 1, 1)
+
+branch5x5 = conv2D_bn(x, 48, 1, 1)
+branch5x5 = conv2D_bn(branch5x5, 64, 5, 5)
+
+branch3x3dbl = conv2D_bn(x, 64, 1, 1)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 64, 1, 1)
+x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed2: 35 x 35 x 288
+
+branch1x1 = conv2D_bn(x, 64, 1, 1)
+
+branch5x5 = conv2D_bn(x, 48, 1, 1)
+branch5x5 = conv2D_bn(branch5x5, 64, 5, 5)
+
+branch3x3dbl = conv2D_bn(x, 64, 1, 1)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 64, 1, 1)
+x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed3: 17 x 17 x 768
+
+branch3x3 = conv2D_bn(x, 384, 3, 3, subsample=(2, 2), border_mode='valid')
+
+branch3x3dbl = conv2D_bn(x, 64, 1, 1)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3, subsample=(2, 2), border_mode='valid')
+
+branch_pool = MaxPooling2D((3, 3), strides=(2, 2), dim_ordering=DIM_ORDERING)(x)
+x = merge([branch3x3, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed4: 17 x 17 x 768
+
+branch1x1 = conv2D_bn(x, 192, 1, 1)
+
+branch7x7 = conv2D_bn(x, 128, 1, 1)
+branch7x7 = conv2D_bn(branch7x7, 128, 1, 7)
+branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
+
+branch7x7dbl = conv2D_bn(x, 128, 1, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 128, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 128, 1, 7)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 128, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
+x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed5: 17 x 17 x 768
+
+branch1x1 = conv2D_bn(x, 192, 1, 1)
+
+branch7x7 = conv2D_bn(x, 160, 1, 1)
+branch7x7 = conv2D_bn(branch7x7, 160, 1, 7)
+branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
+
+branch7x7dbl = conv2D_bn(x, 160, 1, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 1, 7)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
+x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed5: 17 x 17 x 768
+
+branch1x1 = conv2D_bn(x, 192, 1, 1)
+
+branch7x7 = conv2D_bn(x, 160, 1, 1)
+branch7x7 = conv2D_bn(branch7x7, 160, 1, 7)
+branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
+
+branch7x7dbl = conv2D_bn(x, 160, 1, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 1, 7)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
+x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed6: 17 x 17 x 768
+
+branch1x1 = conv2D_bn(x, 192, 1, 1)
+
+branch7x7 = conv2D_bn(x, 160, 1, 1)
+branch7x7 = conv2D_bn(branch7x7, 160, 1, 7)
+branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
+
+branch7x7dbl = conv2D_bn(x, 160, 1, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
+x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed7: 17 x 17 x 768
+
+branch1x1 = conv2D_bn(x, 192, 1, 1)
+
+branch7x7 = conv2D_bn(x, 192, 1, 1)
+branch7x7 = conv2D_bn(branch7x7, 192, 1, 7)
+branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
+
+branch7x7dbl = conv2D_bn(x, 160, 1, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 7, 1)
+branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
+x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# Auxiliary head
+
+aux_logits = AveragePooling2D((5, 5), strides=(3, 3), dim_ordering=DIM_ORDERING)(x)
+aux_logits = conv2D_bn(aux_logits, 128, 1, 1)
+aux_logits = conv2D_bn(aux_logits, 728, 5, 5, border_mode='valid')
+aux_logits = Flatten()(aux_logits)
+aux_preds = Dense(NB_CLASS, activation='softmax')(aux_logits)
+
+# mixed8: 8 x 8 x 1280
+
+branch3x3 = conv2D_bn(x, 192, 1, 1)
+branch3x3 = conv2D_bn(branch3x3, 320, 3, 3, subsample=(2, 2), border_mode='valid')
+
+branch7x7x3 = conv2D_bn(x, 192, 1, 1)
+branch7x7x3 = conv2D_bn(branch7x7x3, 192, 1, 7)
+branch7x7x3 = conv2D_bn(branch7x7x3, 192, 7, 1)
+branch7x7x3 = conv2D_bn(branch7x7x3, 192, 3, 3, subsample=(2, 2), border_mode='valid')
+
+branch_pool = AveragePooling2D((3, 3), strides=(2, 2), dim_ordering=DIM_ORDERING)(x)
+x = merge([branch3x3, branch7x7x3, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed9: 8 x 8 x 2048
+
+branch1x1 = conv2D_bn(x, 320, 1, 1)
+
+branch3x3 = conv2D_bn(x, 384, 1, 1)
+branch3x3_1 = conv2D_bn(branch3x3, 384, 1, 3)
+branch3x3_2 = conv2D_bn(branch3x3, 384, 3, 1)
+branch3x3 = merge([branch3x3_1, branch3x3_2], mode='concat', concat_axis=CONCAT_AXIS)
+
+branch3x3dbl = conv2D_bn(x, 448, 1, 1)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 384, 3, 3)
+branch3x3dbl_1 = conv2D_bn(branch3x3dbl, 384, 1, 3)
+branch3x3dbl_2 = conv2D_bn(branch3x3dbl, 384, 3, 1)
+branch3x3dbl = merge([branch3x3dbl_1, branch3x3dbl_2], mode='concat', concat_axis=CONCAT_AXIS)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
+x = merge([branch1x1, branch3x3, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# mixed10: 8 x 8 x 2048
+
+branch1x1 = conv2D_bn(x, 320, 1, 1)
+
+branch3x3 = conv2D_bn(x, 384, 1, 1)
+branch3x3_1 = conv2D_bn(branch3x3, 384, 1, 3)
+branch3x3_2 = conv2D_bn(branch3x3, 384, 3, 1)
+branch3x3 = merge([branch3x3_1, branch3x3_2], mode='concat', concat_axis=CONCAT_AXIS)
+
+branch3x3dbl = conv2D_bn(x, 448, 1, 1)
+branch3x3dbl = conv2D_bn(branch3x3dbl, 384, 3, 3)
+branch3x3dbl_1 = conv2D_bn(branch3x3dbl, 384, 1, 3)
+branch3x3dbl_2 = conv2D_bn(branch3x3dbl, 384, 3, 1)
+branch3x3dbl = merge([branch3x3dbl_1, branch3x3dbl_2], mode='concat', concat_axis=CONCAT_AXIS)
+
+branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
+branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
+x = merge([branch1x1, branch3x3, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
+
+# Final pooling and prediction
+
+x = AveragePooling2D((8, 8), strides=(1, 1), dim_ordering=DIM_ORDERING)(x)
+x = Dropout(0.5)(x)
+x = Flatten()(x)
+preds = Dense(NB_CLASS, activation='softmax')(x)
+
+# Define model
+
+model = Model(input=img_input, output=[preds, aux_preds])
+model.compile('rmsprop', 'categorical_crossentropy')
+
+# train via e.g. `model.fit(x_train, [y_train] * 2, batch_size=32, nb_epoch=100)`
+# Note that for a large dataset it would be preferable
+# to train using `fit_generator` (see Keras docs).

examples/kaggle_otto_nn.py

@@ -1,121 +0,0 @@
-'''This demonstrates how to reach a score of 0.4890 (local validation)
-on the Kaggle Otto challenge, with a deep net using Keras.
-
-Requires Scikit-Learn and Pandas.
-
-Recommended to run on GPU:
-    Command: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python kaggle_otto_nn.py
-    On EC2 g2.2xlarge instance: 19s/epoch. 6-7 minutes total training time.
-
-Best validation score at epoch 21: 0.4881
-
-Try it at home:
-    - with/without BatchNormalization (BatchNormalization helps!)
-    - with ReLU or with PReLU (PReLU helps!)
-    - with smaller layers, largers layers
-    - with more layers, less layers
-    - with different optimizers (SGD+momentum+decay is probably better than Adam!)
-
-Get the data from Kaggle:
-https://www.kaggle.com/c/otto-group-product-classification-challenge/data
-'''
-
-from __future__ import print_function
-import numpy as np
-import pandas as pd
-np.random.seed(1337)  # for reproducibility
-
-from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation
-from keras.layers.normalization import BatchNormalization
-from keras.layers.advanced_activations import PReLU
-from keras.utils import np_utils, generic_utils
-
-from sklearn.preprocessing import LabelEncoder
-from sklearn.preprocessing import StandardScaler
-
-
-def load_data(path, train=True):
-    df = pd.read_csv(path)
-    X = df.values.copy()
-    if train:
-        np.random.shuffle(X)  # https://youtu.be/uyUXoap67N8
-        X, labels = X[:, 1:-1].astype(np.float32), X[:, -1]
-        return X, labels
-    else:
-        X, ids = X[:, 1:].astype(np.float32), X[:, 0].astype(str)
-        return X, ids
-
-
-def preprocess_data(X, scaler=None):
-    if not scaler:
-        scaler = StandardScaler()
-        scaler.fit(X)
-    X = scaler.transform(X)
-    return X, scaler
-
-
-def preprocess_labels(labels, encoder=None, categorical=True):
-    if not encoder:
-        encoder = LabelEncoder()
-        encoder.fit(labels)
-    y = encoder.transform(labels).astype(np.int32)
-    if categorical:
-        y = np_utils.to_categorical(y)
-    return y, encoder
-
-
-def make_submission(y_prob, ids, encoder, fname):
-    with open(fname, 'w') as f:
-        f.write('id,')
-        f.write(','.join([str(i) for i in encoder.classes_]))
-        f.write('\n')
-        for i, probs in zip(ids, y_prob):
-            probas = ','.join([i] + [str(p) for p in probs.tolist()])
-            f.write(probas)
-            f.write('\n')
-    print('Wrote submission to file {}.'.format(fname))
-
-print('Loading data...')
-X, labels = load_data('train.csv', train=True)
-X, scaler = preprocess_data(X)
-y, encoder = preprocess_labels(labels)
-
-X_test, ids = load_data('test.csv', train=False)
-X_test, _ = preprocess_data(X_test, scaler)
-
-nb_classes = y.shape[1]
-print(nb_classes, 'classes')
-
-dims = X.shape[1]
-print(dims, 'dims')
-
-print('Building model...')
-
-model = Sequential()
-model.add(Dense(512, input_shape=(dims,)))
-model.add(PReLU())
-model.add(BatchNormalization())
-model.add(Dropout(0.5))
-
-model.add(Dense(512))
-model.add(PReLU())
-model.add(BatchNormalization())
-model.add(Dropout(0.5))
-
-model.add(Dense(512))
-model.add(PReLU())
-model.add(BatchNormalization())
-model.add(Dropout(0.5))
-
-model.add(Dense(nb_classes))
-model.add(Activation('softmax'))
-
-model.compile(loss='categorical_crossentropy', optimizer='adam')
-
-print('Training model...')
-model.fit(X, y, nb_epoch=20, batch_size=128, validation_split=0.15)
-
-print('Generating submission...')
-proba = model.predict_proba(X_test)
-make_submission(proba, ids, encoder, fname='keras-otto.csv')

examples/lstm_benchmark.py

@@ -0,0 +1,83 @@
+'''Compare LSTM implementations on the IMDB sentiment classification task.
+
+consume_less='cpu' preprocesses input to the LSTM which typically results in
+faster computations at the expense of increased peak memory usage as the
+preprocessed input must be kept in memory.
+
+consume_less='mem' does away with the preprocessing, meaning that it might take
+a little longer, but should require less peak memory.
+
+consume_less='gpu' concatenates the input, output and forget gate's weights
+into one, large matrix, resulting in faster computation time as the GPU can
+utilize more cores, at the expense of reduced regularization because the same
+dropout is shared across the gates.
+
+Note that the relative performance of the different `consume_less` modes
+can vary depending on your device, your model and the size of your data.
+'''
+
+import time
+import numpy as np
+import matplotlib.pyplot as plt
+
+from keras.preprocessing import sequence
+from keras.models import Sequential
+from keras.layers import Embedding, Dense, LSTM
+from keras.datasets import imdb
+
+max_features = 20000
+max_length = 80
+embedding_dim = 256
+batch_size = 128
+epochs = 10
+modes = ['cpu', 'mem', 'gpu']
+
+print('Loading data...')
+(X_train, y_train), (X_test, y_test) = imdb.load_data(nb_words=max_features)
+X_train = sequence.pad_sequences(X_train, max_length)
+X_test = sequence.pad_sequences(X_test, max_length)
+
+# Compile and train different models while meauring performance.
+results = []
+for mode in modes:
+    print('Testing mode: consume_less="{}"'.format(mode))
+
+    model = Sequential()
+    model.add(Embedding(max_features, embedding_dim, input_length=max_length, dropout=0.2))
+    model.add(LSTM(embedding_dim, dropout_W=0.2, dropout_U=0.2, consume_less=mode))
+    model.add(Dense(1, activation='sigmoid'))
+    model.compile(loss='binary_crossentropy',
+                  optimizer='adam',
+                  metrics=['accuracy'])
+
+    start_time = time.time()
+    history = model.fit(X_train, y_train,
+                        batch_size=batch_size,
+                        nb_epoch=epochs,
+                        validation_data=(X_test, y_test))
+    average_time_per_epoch = (time.time() - start_time) / epochs
+
+    results.append((history, average_time_per_epoch))
+
+# Compare models' accuracy, loss and elapsed time per epoch.
+plt.style.use('ggplot')
+ax1 = plt.subplot2grid((2, 2), (0, 0))
+ax1.set_title('Accuracy')
+ax1.set_ylabel('Validation Accuracy')
+ax1.set_xlabel('Epochs')
+ax2 = plt.subplot2grid((2, 2), (1, 0))
+ax2.set_title('Loss')
+ax2.set_ylabel('Validation Loss')
+ax2.set_xlabel('Epochs')
+ax3 = plt.subplot2grid((2, 2), (0, 1), rowspan=2)
+ax3.set_title('Time')
+ax3.set_ylabel('Seconds')
+for mode, result in zip(modes, results):
+    ax1.plot(result[0].epoch, result[0].history['val_acc'], label=mode)
+    ax2.plot(result[0].epoch, result[0].history['val_loss'], label=mode)
+ax1.legend()
+ax2.legend()
+ax3.bar(np.arange(len(results)), [x[1] for x in results],
+        tick_label=modes, align='center')
+plt.tight_layout()
+plt.show()

examples/lstm_text_generation.py

@@ -12,9 +12,9 @@ has at least ~100k characters. ~1M is better.
 
 from __future__ import print_function
 from keras.models import Sequential
-from keras.layers.core import Dense, Activation, Dropout
-from keras.layers.recurrent import LSTM
-from keras.datasets.data_utils import get_file
+from keras.layers import Dense, Activation, Dropout
+from keras.layers import LSTM
+from keras.utils.data_utils import get_file
 import numpy as np
 import random
 import sys
@@ -29,7 +29,7 @@ char_indices = dict((c, i) for i, c in enumerate(chars))
 indices_char = dict((i, c) for i, c in enumerate(chars))
 
 # cut the text in semi-redundant sequences of maxlen characters
-maxlen = 20
+maxlen = 40
 step = 3
 sentences = []
 next_chars = []

examples/mnist_cnn.py

@@ -1,8 +1,7 @@
-'''Train a simple convnet on the MNIST dataset.
+'''Trains a simple convnet on the MNIST dataset.
 
-Run on GPU: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python mnist_cnn.py
-
-Get to 99.25% test accuracy after 12 epochs (there is still a lot of margin for parameter tuning).
+Gets to 99.25% test accuracy after 12 epochs
+(there is still a lot of margin for parameter tuning).
 16 seconds per epoch on a GRID K520 GPU.
 '''
 
@@ -12,8 +11,8 @@ np.random.seed(1337)  # for reproducibility
 
 from keras.datasets import mnist
 from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation, Flatten
-from keras.layers.convolutional import Convolution2D, MaxPooling2D
+from keras.layers import Dense, Dropout, Activation, Flatten
+from keras.layers import Convolution2D, MaxPooling2D
 from keras.utils import np_utils
 
 batch_size = 128
@@ -29,7 +28,7 @@ nb_pool = 2
 # convolution kernel size
 nb_conv = 3
 
-# the data, shuffled and split between tran and test sets
+# the data, shuffled and split between train and test sets
 (X_train, y_train), (X_test, y_test) = mnist.load_data()
 
 X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
@@ -64,10 +63,12 @@ model.add(Dropout(0.5))
 model.add(Dense(nb_classes))
 model.add(Activation('softmax'))
 
-model.compile(loss='categorical_crossentropy', optimizer='adadelta')
+model.compile(loss='categorical_crossentropy',
+              optimizer='adadelta',
+              metrics=['accuracy'])
 
 model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
-          show_accuracy=True, verbose=1, validation_data=(X_test, Y_test))
-score = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)
+          verbose=1, validation_data=(X_test, Y_test))
+score = model.evaluate(X_test, Y_test, verbose=0)
 print('Test score:', score[0])
 print('Test accuracy:', score[1])

examples/mnist_irnn.py

@@ -14,18 +14,15 @@ Reaches 0.93 train/test accuracy after 900 epochs
 '''
 
 from __future__ import print_function
-import numpy as np
-np.random.seed(1337)  # for reproducibility
 
 from keras.datasets import mnist
 from keras.models import Sequential
-from keras.layers.core import Dense, Activation
+from keras.layers import Dense, Activation
+from keras.layers import SimpleRNN
 from keras.initializations import normal, identity
-from keras.layers.recurrent import SimpleRNN, LSTM
 from keras.optimizers import RMSprop
 from keras.utils import np_utils
 
-
 batch_size = 32
 nb_classes = 10
 nb_epochs = 200
@@ -54,32 +51,20 @@ Y_test = np_utils.to_categorical(y_test, nb_classes)
 print('Evaluate IRNN...')
 model = Sequential()
 model.add(SimpleRNN(output_dim=hidden_units,
-                    init=lambda shape: normal(shape, scale=0.001),
-                    inner_init=lambda shape: identity(shape, scale=1.0),
-                    activation='relu', input_shape=X_train.shape[1:]))
+                    init=lambda shape, name: normal(shape, scale=0.001, name=name),
+                    inner_init=lambda shape, name: identity(shape, scale=1.0, name=name),
+                    activation='relu',
+                    input_shape=X_train.shape[1:]))
 model.add(Dense(nb_classes))
 model.add(Activation('softmax'))
 rmsprop = RMSprop(lr=learning_rate)
-model.compile(loss='categorical_crossentropy', optimizer=rmsprop)
+model.compile(loss='categorical_crossentropy',
+              optimizer=rmsprop,
+              metrics=['accuracy'])
 
 model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epochs,
-          show_accuracy=True, verbose=1, validation_data=(X_test, Y_test))
+          verbose=1, validation_data=(X_test, Y_test))
 
-scores = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)
+scores = model.evaluate(X_test, Y_test, verbose=0)
 print('IRNN test score:', scores[0])
 print('IRNN test accuracy:', scores[1])
-
-print('Compare to LSTM...')
-model = Sequential()
-model.add(LSTM(hidden_units, input_shape=X_train.shape[1:]))
-model.add(Dense(nb_classes))
-model.add(Activation('softmax'))
-rmsprop = RMSprop(lr=learning_rate)
-model.compile(loss='categorical_crossentropy', optimizer=rmsprop)
-
-model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epochs,
-          show_accuracy=True, verbose=1, validation_data=(X_test, Y_test))
-
-scores = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)
-print('LSTM test score:', scores[0])
-print('LSTM test accuracy:', scores[1])

examples/mnist_mlp.py

@@ -1,6 +1,6 @@
-'''Train a simple deep NN on the MNIST dataset.
+'''Trains a simple deep NN on the MNIST dataset.
 
-Get to 98.40% test accuracy after 20 epochs
+Gets to 98.40% test accuracy after 20 epochs
 (there is *a lot* of margin for parameter tuning).
 2 seconds per epoch on a K520 GPU.
 '''
@@ -20,7 +20,7 @@ batch_size = 128
 nb_classes = 10
 nb_epoch = 20
 
-# the data, shuffled and split between tran and test sets
+# the data, shuffled and split between train and test sets
 (X_train, y_train), (X_test, y_test) = mnist.load_data()
 
 X_train = X_train.reshape(60000, 784)
@@ -46,14 +46,15 @@ model.add(Dropout(0.2))
 model.add(Dense(10))
 model.add(Activation('softmax'))
 
-rms = RMSprop()
-model.compile(loss='categorical_crossentropy', optimizer=rms)
+model.summary()
 
-model.fit(X_train, Y_train,
-          batch_size=batch_size, nb_epoch=nb_epoch,
-          show_accuracy=True, verbose=2,
-          validation_data=(X_test, Y_test))
-score = model.evaluate(X_test, Y_test,
-                       show_accuracy=True, verbose=0)
+model.compile(loss='categorical_crossentropy',
+              optimizer=RMSprop(),
+              metrics=['accuracy'])
+
+history = model.fit(X_train, Y_train,
+                    batch_size=batch_size, nb_epoch=nb_epoch,
+                    verbose=1, validation_data=(X_test, Y_test))
+score = model.evaluate(X_test, Y_test, verbose=0)
 print('Test score:', score[0])
 print('Test accuracy:', score[1])

examples/mnist_siamese_graph.py

@@ -7,8 +7,6 @@ for mode details).
 [1] "Dimensionality Reduction by Learning an Invariant Mapping"
     http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf
 
-Run on GPU: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python mnist_siamese_graph.py
-
 Gets to 99.5% test accuracy after 20 epochs.
 3 seconds per epoch on a Titan X GPU
 '''
@@ -19,25 +17,28 @@ np.random.seed(1337)  # for reproducibility
 
 import random
 from keras.datasets import mnist
-from keras.models import Sequential, Graph
-from keras.layers.core import Dense, Dropout, Lambda
+from keras.models import Sequential, Model
+from keras.layers import Dense, Dropout, Input, Lambda
 from keras.optimizers import SGD, RMSprop
 from keras import backend as K
 
 
-def euclidean_distance(inputs):
-    assert len(inputs) == 2, ('Euclidean distance needs '
-                              '2 inputs, %d given' % len(inputs))
-    u, v = inputs.values()
-    return K.sqrt(K.sum(K.square(u - v), axis=1, keepdims=True))
+def euclidean_distance(vects):
+    x, y = vects
+    return K.sqrt(K.sum(K.square(x - y), axis=1, keepdims=True))
 
 
-def contrastive_loss(y, d):
+def eucl_dist_output_shape(shapes):
+    shape1, shape2 = shapes
+    return (shape1[0], 1)
+
+
+def contrastive_loss(y_true, y_pred):
     '''Contrastive loss from Hadsell-et-al.'06
     http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf
     '''
     margin = 1
-    return K.mean(y * K.square(d) + (1 - y) * K.square(K.maximum(margin - d, 0)))
+    return K.mean(y_true * K.square(y_pred) + (1 - y_true) * K.square(K.maximum(margin - y_pred, 0)))
 
 
 def create_pairs(x, digit_indices):
@@ -77,7 +78,7 @@ def compute_accuracy(predictions, labels):
     return labels[predictions.ravel() < 0.5].mean()
 
 
-# the data, shuffled and split between tran and test sets
+# the data, shuffled and split between train and test sets
 (X_train, y_train), (X_test, y_test) = mnist.load_data()
 X_train = X_train.reshape(60000, 784)
 X_test = X_test.reshape(10000, 784)
@@ -98,26 +99,31 @@ te_pairs, te_y = create_pairs(X_test, digit_indices)
 # network definition
 base_network = create_base_network(input_dim)
 
-g = Graph()
-g.add_input(name='input_a', input_shape=(input_dim,))
-g.add_input(name='input_b', input_shape=(input_dim,))
-g.add_shared_node(base_network, name='shared', inputs=['input_a', 'input_b'],
-                  merge_mode='join')
-g.add_node(Lambda(euclidean_distance), name='d', input='shared')
-g.add_output(name='output', input='d')
+input_a = Input(shape=(input_dim,))
+input_b = Input(shape=(input_dim,))
+
+# because we re-use the same instance `base_network`,
+# the weights of the network
+# will be shared across the two branches
+processed_a = base_network(input_a)
+processed_b = base_network(input_b)
+
+distance = Lambda(euclidean_distance, output_shape=eucl_dist_output_shape)([processed_a, processed_b])
+
+model = Model(input=[input_a, input_b], output=distance)
 
 # train
 rms = RMSprop()
-g.compile(loss={'output': contrastive_loss}, optimizer=rms)
-g.fit({'input_a': tr_pairs[:, 0], 'input_b': tr_pairs[:, 1], 'output': tr_y},
-      validation_data={'input_a': te_pairs[:, 0], 'input_b': te_pairs[:, 1], 'output': te_y},
-      batch_size=128,
-      nb_epoch=nb_epoch)
+model.compile(loss=contrastive_loss, optimizer=rms)
+model.fit([tr_pairs[:, 0], tr_pairs[:, 1]], tr_y,
+          validation_data=([te_pairs[:, 0], te_pairs[:, 1]], te_y),
+          batch_size=128,
+          nb_epoch=nb_epoch)
 
 # compute final accuracy on training and test sets
-pred = g.predict({'input_a': tr_pairs[:, 0], 'input_b': tr_pairs[:, 1]})['output']
+pred = model.predict([tr_pairs[:, 0], tr_pairs[:, 1]])
 tr_acc = compute_accuracy(pred, tr_y)
-pred = g.predict({'input_a': te_pairs[:, 0], 'input_b': te_pairs[:, 1]})['output']
+pred = model.predict([te_pairs[:, 0], te_pairs[:, 1]])
 te_acc = compute_accuracy(pred, te_y)
 
 print('* Accuracy on training set: %0.2f%%' % (100 * tr_acc))

examples/mnist_sklearn_wrapper.py

@@ -0,0 +1,94 @@
+'''Example of how to use sklearn wrapper
+
+Builds simple CNN models on MNIST and uses sklearn's GridSearchCV to find best model
+'''
+
+from __future__ import print_function
+import numpy as np
+np.random.seed(1337)  # for reproducibility
+
+from keras.datasets import mnist
+from keras.models import Sequential
+from keras.layers import Dense, Dropout, Activation, Flatten
+from keras.layers import Convolution2D, MaxPooling2D
+from keras.utils import np_utils
+from keras.wrappers.scikit_learn import KerasClassifier
+from sklearn.grid_search import GridSearchCV
+
+
+nb_classes = 10
+
+# input image dimensions
+img_rows, img_cols = 28, 28
+
+# load training data and do basic data normalization
+(X_train, y_train), (X_test, y_test) = mnist.load_data()
+X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
+X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
+X_train = X_train.astype('float32')
+X_test = X_test.astype('float32')
+X_train /= 255
+X_test /= 255
+
+# convert class vectors to binary class matrices
+y_train = np_utils.to_categorical(y_train, nb_classes)
+y_test = np_utils.to_categorical(y_test, nb_classes)
+
+def make_model(dense_layer_sizes, nb_filters, nb_conv, nb_pool):
+    '''Creates model comprised of 2 convolutional layers followed by dense layers
+
+    dense_layer_sizes: List of layer sizes. This list has one number for each layer
+    nb_filters: Number of convolutional filters in each convolutional layer
+    nb_conv: Convolutional kernel size
+    nb_pool: Size of pooling area for max pooling
+    '''
+
+    model = Sequential()
+
+    model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
+                            border_mode='valid',
+                            input_shape=(1, img_rows, img_cols)))
+    model.add(Activation('relu'))
+    model.add(Convolution2D(nb_filters, nb_conv, nb_conv))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
+    model.add(Dropout(0.25))
+
+    model.add(Flatten())
+    for layer_size in dense_layer_sizes:
+        model.add(Dense(layer_size))
+    model.add(Activation('relu'))
+    model.add(Dropout(0.5))
+    model.add(Dense(nb_classes))
+    model.add(Activation('softmax'))
+
+    model.compile(loss='categorical_crossentropy',
+                  optimizer='adadelta',
+                  metrics=['accuracy'])
+
+    return model
+
+dense_size_candidates = [[32], [64], [32, 32], [64, 64]]
+my_classifier = KerasClassifier(make_model, batch_size=32)
+validator = GridSearchCV(my_classifier,
+                         param_grid={'dense_layer_sizes': dense_size_candidates,
+                                     # nb_epoch is avail for tuning even when not
+                                     # an argument to model building function
+                                     'nb_epoch': [3, 6],
+                                     'nb_filters': [8],
+                                     'nb_conv': [3],
+                                     'nb_pool': [2]},
+                         scoring='log_loss',
+                         n_jobs=1)
+validator.fit(X_train, y_train)
+
+print('The parameters of the best model are: ')
+print(validator.best_params_)
+
+# validator.best_estimator_ returns sklearn-wrapped version of best model.
+# validator.best_estimator_.model returns the (unwrapped) keras model
+best_model = validator.best_estimator_.model
+metric_names = best_model.metrics_names
+metric_values = best_model.evaluate(X_test, y_test)
+for metric, value in zip(metric_names, metric_values):
+    print(metric, ': ', value)

examples/mnist_transfer_cnn.py

@@ -19,8 +19,8 @@ np.random.seed(1337)  # for reproducibility
 
 from keras.datasets import mnist
 from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation, Flatten
-from keras.layers.convolutional import Convolution2D, MaxPooling2D
+from keras.layers import Dense, Dropout, Activation, Flatten
+from keras.layers import Convolution2D, MaxPooling2D
 from keras.utils import np_utils
 
 
@@ -55,15 +55,17 @@ def train_model(model, train, test, nb_classes):
     Y_train = np_utils.to_categorical(train[1], nb_classes)
     Y_test = np_utils.to_categorical(test[1], nb_classes)
 
-    model.compile(loss='categorical_crossentropy', optimizer='adadelta')
+    model.compile(loss='categorical_crossentropy',
+                  optimizer='adadelta',
+                  metrics=['accuracy'])
 
     t = now()
     model.fit(X_train, Y_train,
               batch_size=batch_size, nb_epoch=nb_epoch,
-              show_accuracy=True, verbose=1,
+              verbose=1,
               validation_data=(X_test, Y_test))
     print('Training time: %s' % (now() - t))
-    score = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)
+    score = model.evaluate(X_test, Y_test, verbose=0)
     print('Test score:', score[0])
     print('Test accuracy:', score[1])
 

examples/neural_style_transfer.py

@@ -7,11 +7,11 @@ and make sure the variable `weights_path` in this script matches the location of
 
 Run the script with:
 ```
-python neural_style.py path_to_your_base_image.jpg path_to_your_reference.jpg prefix_for_results
+python neural_style_transfer.py path_to_your_base_image.jpg path_to_your_reference.jpg prefix_for_results
 ```
 e.g.:
 ```
-python neural_style.py img/tuebingen.jpg img/starry_night.jpg results/my_result
+python neural_style_transfer.py img/tuebingen.jpg img/starry_night.jpg results/my_result
 ```
 
 It is preferrable to run this script on GPU, for speed.
@@ -58,7 +58,7 @@ import argparse
 import h5py
 
 from keras.models import Sequential
-from keras.layers.convolutional import Convolution2D, ZeroPadding2D, MaxPooling2D
+from keras.layers import Convolution2D, ZeroPadding2D, MaxPooling2D
 from keras import backend as K
 
 parser = argparse.ArgumentParser(description='Neural style transfer with Keras.')
@@ -89,17 +89,11 @@ assert img_height == img_width, 'Due to the use of the Gram matrix, width and he
 def preprocess_image(image_path):
     img = imresize(imread(image_path), (img_width, img_height))
     img = img.transpose((2, 0, 1)).astype('float64')
-    img[:, :, 0] -= 103.939
-    img[:, :, 1] -= 116.779
-    img[:, :, 2] -= 123.68
     img = np.expand_dims(img, axis=0)
     return img
 
 # util function to convert a tensor into a valid image
 def deprocess_image(x):
-    x[:, :, 0] += 103.939
-    x[:, :, 1] += 116.779
-    x[:, :, 2] += 123.68
     x = x.transpose((1, 2, 0))
     x = np.clip(x, 0, 255).astype('uint8')
     return x
@@ -117,8 +111,8 @@ input_tensor = K.concatenate([base_image,
                               combination_image], axis=0)
 
 # build the VGG16 network with our 3 images as input
-first_layer = ZeroPadding2D((1, 1), input_shape=(3, img_width, img_height))
-first_layer.input = input_tensor
+first_layer = ZeroPadding2D((1, 1))
+first_layer.set_input(input_tensor, shape=(3, 3, img_width, img_height))
 
 model = Sequential()
 model.add(first_layer)
@@ -174,7 +168,7 @@ f.close()
 print('Model loaded.')
 
 # get the symbolic outputs of each "key" layer (we gave them unique names).
-outputs_dict = dict([(layer.name, layer.get_output()) for layer in model.layers])
+outputs_dict = dict([(layer.name, layer.output) for layer in model.layers])
 
 # compute the neural style loss
 # first we need to define 4 util functions

examples/reuters_mlp.py

@@ -1,8 +1,5 @@
-'''Train and evaluate a simple MLP on the Reuters newswire topic classification task.
-GPU run command:
-    THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python examples/reuters_mlp.py
-CPU run command:
-    python examples/reuters_mlp.py
+'''Trains and evaluate a simple MLP
+on the Reuters newswire topic classification task.
 '''
 
 from __future__ import print_function
@@ -11,8 +8,7 @@ np.random.seed(1337)  # for reproducibility
 
 from keras.datasets import reuters
 from keras.models import Sequential
-from keras.layers.core import Dense, Dropout, Activation
-from keras.layers.normalization import BatchNormalization
+from keras.layers import Dense, Dropout, Activation
 from keras.utils import np_utils
 from keras.preprocessing.text import Tokenizer
 
@@ -49,9 +45,14 @@ model.add(Dropout(0.5))
 model.add(Dense(nb_classes))
 model.add(Activation('softmax'))
 
-model.compile(loss='categorical_crossentropy', optimizer='adam')
+model.compile(loss='categorical_crossentropy',
+              optimizer='adam',
+              metrics=['accuracy'])
 
-history = model.fit(X_train, Y_train, nb_epoch=nb_epoch, batch_size=batch_size, verbose=1, show_accuracy=True, validation_split=0.1)
-score = model.evaluate(X_test, Y_test, batch_size=batch_size, verbose=1, show_accuracy=True)
+history = model.fit(X_train, Y_train,
+                    nb_epoch=nb_epoch, batch_size=batch_size,
+                    verbose=1, validation_split=0.1)
+score = model.evaluate(X_test, Y_test,
+                       batch_size=batch_size, verbose=1)
 print('Test score:', score[0])
 print('Test accuracy:', score[1])

examples/stateful_lstm.py

@@ -5,8 +5,7 @@ from __future__ import print_function
 import numpy as np
 import matplotlib.pyplot as plt
 from keras.models import Sequential
-from keras.layers.core import Dense
-from keras.layers.recurrent import LSTM
+from keras.layers import Dense, LSTM
 
 
 # since we are using stateful rnn tsteps can be set to 1
@@ -59,7 +58,7 @@ model.add(LSTM(50,
                return_sequences=False,
                stateful=True))
 model.add(Dense(1))
-model.compile(loss='rmse', optimizer='rmsprop')
+model.compile(loss='mse', optimizer='rmsprop')
 
 print('Training')
 for i in range(epochs):
@@ -68,7 +67,8 @@ for i in range(epochs):
               expected_output,
               batch_size=batch_size,
               verbose=1,
-              nb_epoch=1)
+              nb_epoch=1,
+              shuffle=False)
     model.reset_states()
 
 print('Predicting')

examples/variational_autoencoder.py

@@ -0,0 +1,98 @@
+'''This script demonstrates how to build a variational autoencoder with Keras.
+
+Reference: "Auto-Encoding Variational Bayes" https://arxiv.org/abs/1312.6114
+'''
+import numpy as np
+import matplotlib.pyplot as plt
+
+from keras.layers import Input, Dense, Lambda
+from keras.models import Model
+from keras import backend as K
+from keras import objectives
+from keras.datasets import mnist
+
+batch_size = 16
+original_dim = 784
+latent_dim = 2
+intermediate_dim = 128
+epsilon_std = 0.01
+nb_epoch = 40
+
+x = Input(batch_shape=(batch_size, original_dim))
+h = Dense(intermediate_dim, activation='relu')(x)
+z_mean = Dense(latent_dim)(h)
+z_log_sigma = Dense(latent_dim)(h)
+
+def sampling(args):
+    z_mean, z_log_sigma = args
+    epsilon = K.random_normal(shape=(batch_size, latent_dim),
+                              mean=0., std=epsilon_std)
+    return z_mean + K.exp(z_log_sigma) * epsilon
+
+# note that "output_shape" isn't necessary with the TensorFlow backend
+# so you could write `Lambda(sampling)([z_mean, z_log_sigma])`
+z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_sigma])
+
+# we instantiate these layers separately so as to reuse them later
+decoder_h = Dense(intermediate_dim, activation='relu')
+decoder_mean = Dense(original_dim, activation='sigmoid')
+h_decoded = decoder_h(z)
+x_decoded_mean = decoder_mean(h_decoded)
+
+def vae_loss(x, x_decoded_mean):
+    xent_loss = objectives.binary_crossentropy(x, x_decoded_mean)
+    kl_loss = - 0.5 * K.mean(1 + z_log_sigma - K.square(z_mean) - K.exp(z_log_sigma), axis=-1)
+    return xent_loss + kl_loss
+
+vae = Model(x, x_decoded_mean)
+vae.compile(optimizer='rmsprop', loss=vae_loss)
+
+# train the VAE on MNIST digits
+(x_train, y_train), (x_test, y_test) = mnist.load_data()
+
+x_train = x_train.astype('float32') / 255.
+x_test = x_test.astype('float32') / 255.
+x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))
+x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:])))
+
+vae.fit(x_train, x_train,
+        shuffle=True,
+        nb_epoch=nb_epoch,
+        batch_size=batch_size,
+        validation_data=(x_test, x_test))
+
+# build a model to project inputs on the latent space
+encoder = Model(x, z_mean)
+
+# display a 2D plot of the digit classes in the latent space
+x_test_encoded = encoder.predict(x_test, batch_size=batch_size)
+plt.figure(figsize=(6, 6))
+plt.scatter(x_test_encoded[:, 0], x_test_encoded[:, 1], c=y_test)
+plt.colorbar()
+plt.show()
+
+# build a digit generator that can sample from the learned distribution
+decoder_input = Input(shape=(latent_dim,))
+_h_decoded = decoder_h(decoder_input)
+_x_decoded_mean = decoder_mean(_h_decoded)
+generator = Model(decoder_input, _x_decoded_mean)
+
+# display a 2D manifold of the digits
+n = 15  # figure with 15x15 digits
+digit_size = 28
+figure = np.zeros((digit_size * n, digit_size * n))
+# we will sample n points within [-15, 15] standard deviations
+grid_x = np.linspace(-15, 15, n)
+grid_y = np.linspace(-15, 15, n)
+
+for i, yi in enumerate(grid_x):
+    for j, xi in enumerate(grid_y):
+        z_sample = np.array([[xi, yi]]) * epsilon_std
+        x_decoded = generator.predict(z_sample)
+        digit = x_decoded[0].reshape(digit_size, digit_size)
+        figure[i * digit_size: (i + 1) * digit_size,
+               j * digit_size: (j + 1) * digit_size] = digit
+
+plt.figure(figsize=(10, 10))
+plt.imshow(figure)
+plt.show()

keras/__init__.py

@@ -1 +1,18 @@
-__version__ = '0.3.1'
+from __future__ import absolute_import
+from . import backend
+from . import datasets
+from . import engine
+from . import layers
+from . import preprocessing
+from . import utils
+from . import wrappers
+from . import callbacks
+from . import constraints
+from . import initializations
+from . import metrics
+from . import models
+from . import objectives
+from . import optimizers
+from . import regularizers
+
+__version__ = '1.0.3'

keras/activations.py

@@ -7,13 +7,9 @@ def softmax(x):
     if ndim == 2:
         return K.softmax(x)
     elif ndim == 3:
-        # apply softmax to each timestep
-        def step(x, states):
-            return K.softmax(x), []
-        last_output, outputs, states = K.rnn(step, x,
-                                             [],
-                                             mask=None)
-        return outputs
+        e = K.exp(x - K.max(x, axis=-1, keepdims=True))
+        s = K.sum(e, axis=-1, keepdims=True)
+        return e / s
     else:
         raise Exception('Cannot apply softmax to a tensor that is not 2D or 3D. ' +
                         'Here, ndim=' + str(ndim))
@@ -23,6 +19,10 @@ def softplus(x):
     return K.softplus(x)
 
 
+def softsign(x):
+    return K.softsign(x)
+
+
 def relu(x, alpha=0., max_value=None):
     return K.relu(x, alpha=alpha, max_value=max_value)
 

keras/backend/__init__.py

@@ -3,7 +3,12 @@ from __future__ import print_function
 import os
 import json
 import sys
-from .common import epsilon, floatx, set_epsilon, set_floatx
+from .common import epsilon
+from .common import floatx
+from .common import set_epsilon
+from .common import set_floatx
+from .common import get_uid
+from .common import cast_to_floatx
 
 _keras_base_dir = os.path.expanduser('~')
 if not os.access(_keras_base_dir, os.W_OK):
@@ -18,7 +23,7 @@ _config_path = os.path.expanduser(os.path.join(_keras_dir, 'keras.json'))
 if os.path.exists(_config_path):
     _config = json.load(open(_config_path))
     _floatx = _config.get('floatx', floatx())
-    assert _floatx in {'float32', 'float64'}
+    assert _floatx in {'float16', 'float32', 'float64'}
     _epsilon = _config.get('epsilon', epsilon())
     assert type(_epsilon) == float
     _backend = _config.get('backend', _BACKEND)

keras/backend/common.py

@@ -3,6 +3,7 @@ import numpy as np
 # the type of float to use throughout the session.
 _FLOATX = 'float32'
 _EPSILON = 10e-8
+_UID_PREFIXES = {}
 
 
 def epsilon():
@@ -15,12 +16,15 @@ def set_epsilon(e):
 
 
 def floatx():
+    '''Returns the default float type, as a string
+    (e.g. 'float16', 'float32', 'float64').
+    '''
     return _FLOATX
 
 
 def set_floatx(floatx):
     global _FLOATX
-    if floatx not in {'float32', 'float64'}:
+    if floatx not in {'float16', 'float32', 'float64'}:
         raise Exception('Unknown floatx type: ' + str(floatx))
     floatx = str(floatx)
     _FLOATX = floatx
@@ -30,3 +34,12 @@ def cast_to_floatx(x):
     '''Cast a Numpy array to floatx.
     '''
     return np.asarray(x, dtype=_FLOATX)
+
+
+def get_uid(prefix=''):
+    if prefix not in _UID_PREFIXES:
+        _UID_PREFIXES[prefix] = 1
+        return 1
+    else:
+        _UID_PREFIXES[prefix] += 1
+        return _UID_PREFIXES[prefix]

keras/backend/theano_backend.py

@@ -1,28 +1,25 @@
 import theano
 from theano import tensor as T
 from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
-from theano.tensor.signal import downsample
+from theano.tensor.signal import pool
+from theano.tensor.nnet import conv3d2d
+try:
+    from theano.tensor.nnet.nnet import softsign as T_softsign
+except ImportError:
+    from theano.sandbox.softsign import softsign as T_softsign
+import inspect
 import numpy as np
 from .common import _FLOATX, _EPSILON
 
 
 # INTERNAL UTILS
 theano.config.floatX = _FLOATX
+_LEARNING_PHASE = T.scalar(dtype='uint8', name='keras_learning_phase')  # 0 = test, 1 = train
 
 
-def _on_gpu():
-    '''Return whether the session is set to
-    run on GPU or not (i.e. on CPU).
-    '''
-    return theano.config.device[:3] == 'gpu' or theano.sandbox.cuda.cuda_enabled
-
-
-if _on_gpu():
-    '''Import cuDNN only if running on GPU:
-    not having Cuda installed should not
-    prevent from running the present code.
-    '''
-    from theano.sandbox.cuda import dnn
+def learning_phase():
+    # False = test, True = train
+    return _LEARNING_PHASE
 
 
 # VARIABLE MANIPULATION
@@ -41,8 +38,14 @@ def placeholder(shape=None, ndim=None, dtype=_FLOATX, name=None):
         raise Exception('Specify either a shape or ndim value.')
     if shape is not None:
         ndim = len(shape)
+    else:
+        shape = tuple([None for _ in range(ndim)])
+
     broadcast = (False,) * ndim
-    return T.TensorType(dtype, broadcast)(name)
+    x = T.TensorType(dtype, broadcast)(name)
+    x._keras_shape = shape
+    x._uses_learning_phase = False
+    return x
 
 
 def shape(x):
@@ -58,6 +61,10 @@ def ndim(x):
     return x.ndim
 
 
+def dtype(x):
+    return x.dtype
+
+
 def eval(x):
     '''Run a graph.
     '''
@@ -76,6 +83,12 @@ def ones(shape, dtype=_FLOATX, name=None):
     return variable(np.ones(shape), dtype, name)
 
 
+def eye(size, dtype=_FLOATX, name=None):
+    '''Instantiate an identity matrix.
+    '''
+    return variable(np.eye(size), dtype, name)
+
+
 def ones_like(x):
     return T.ones_like(x)
 
@@ -108,6 +121,38 @@ def dot(x, y):
     return T.dot(x, y)
 
 
+def batch_dot(x, y, axes=None):
+    '''batchwise dot product
+    batch_dot results in a tensor with less dimensions than the input.
+    If the number of dimensions is reduced to 1, we use `expand_dims` to
+    make sure that ndim is at least 2.
+
+    # Example
+        Assume x = [[1, 2]   and y = [[5, 6]
+                    [3, 4]]           [7, 8]]
+        batch_dot(x, y, axes=1) = [[17, 53]] which is the main diagonal
+        of x.dot(y.T), although we never have to calculate the off-diagonal
+        elements.
+
+
+    # Arguments
+        x, y: tensors with ndim >= 2
+        axes: list (or single) int with target dimensions
+
+    # Returns
+        Tensor with ndim >= 2
+    '''
+    if type(axes) == int:
+        axes = (axes, axes)
+    if axes is None:
+        # behaves like tf.batch_matmul as default
+        axes = [x.ndim - 1, y.ndim - 2]
+    out = T.batched_tensordot(x, y, axes=axes)
+    if ndim(out) == 1:
+        out = expand_dims(out, 1)
+    return out
+
+
 def transpose(x):
     return T.transpose(x)
 
@@ -145,7 +190,10 @@ def prod(x, axis=None, keepdims=False):
 
 
 def mean(x, axis=None, keepdims=False):
-    return T.mean(x, axis=axis, keepdims=keepdims)
+    dtype = None
+    if 'int' in x.dtype:
+        dtype = _FLOATX
+    return T.mean(x, axis=axis, keepdims=keepdims, dtype=dtype)
 
 
 def std(x, axis=None, keepdims=False):
@@ -191,6 +239,10 @@ def round(x):
     return T.round(x)
 
 
+def sign(x):
+    return T.sgn(x)
+
+
 def pow(x, a):
     return T.pow(x, a)
 
@@ -217,6 +269,14 @@ def minimum(x, y):
     return T.minimum(x, y)
 
 
+def sin(x):
+    return T.sin(x)
+
+
+def cos(x):
+    return T.cos(x)
+
+
 # SHAPE OPERATIONS
 
 def concatenate(tensors, axis=-1):
@@ -265,6 +325,27 @@ def resize_images(X, height_factor, width_factor, dim_ordering):
         raise Exception('Invalid dim_ordering: ' + dim_ordering)
 
 
+def resize_volumes(X, depth_factor, height_factor, width_factor, dim_ordering):
+    '''Resize the volume contained in a 5D tensor of shape
+    - [batch, channels, depth, height, width] (for 'th' dim_ordering)
+    - [batch, depth, height, width, channels] (for 'tf' dim_ordering)
+    by a factor of (depth_factor, height_factor, width_factor).
+    Both factors should be positive integers.
+    '''
+    if dim_ordering == 'th':
+        output = repeat_elements(X, depth_factor, axis=2)
+        output = repeat_elements(output, height_factor, axis=3)
+        output = repeat_elements(output, width_factor, axis=4)
+        return output
+    elif dim_ordering == 'tf':
+        output = repeat_elements(X, depth_factor, axis=1)
+        output = repeat_elements(output, height_factor, axis=2)
+        output = repeat_elements(output, width_factor, axis=3)
+        return output
+    else:
+        raise Exception('Invalid dim_ordering: ' + dim_ordering)
+
+
 def repeat(x, n):
     '''Repeat a 2D tensor.
 
@@ -357,6 +438,45 @@ def spatial_2d_padding(x, padding=(1, 1), dim_ordering='th'):
         raise Exception('Invalid dim_ordering: ' + dim_ordering)
     return T.set_subtensor(output[indices], x)
 
+
+def spatial_3d_padding(x, padding=(1, 1, 1), dim_ordering='th'):
+    '''Pad the 2nd, 3rd and 4th dimensions of a 5D tensor
+    with "padding[0]", "padding[1]" and "padding[2]" (resp.) zeros left and right.
+    '''
+    input_shape = x.shape
+    if dim_ordering == 'th':
+        output_shape = (input_shape[0],
+                        input_shape[1],
+                        input_shape[2] + 2 * padding[0],
+                        input_shape[3] + 2 * padding[1],
+                        input_shape[4] + 2 * padding[2])
+        output = T.zeros(output_shape)
+        indices = (slice(None),
+                   slice(None),
+                   slice(padding[0], input_shape[2] + padding[0]),
+                   slice(padding[1], input_shape[3] + padding[1]),
+                   slice(padding[2], input_shape[4] + padding[2]))
+
+    elif dim_ordering == 'tf':
+        output_shape = (input_shape[0],
+                        input_shape[1] + 2 * padding[0],
+                        input_shape[2] + 2 * padding[1],
+                        input_shape[3] + 2 * padding[2],
+                        input_shape[4])
+        output = T.zeros(output_shape)
+        indices = (slice(None),
+                   slice(padding[0], input_shape[1] + padding[0]),
+                   slice(padding[1], input_shape[2] + padding[1]),
+                   slice(padding[2], input_shape[3] + padding[2]),
+                   slice(None))
+    else:
+        raise Exception('Invalid dim_ordering: ' + dim_ordering)
+    return T.set_subtensor(output[indices], x)
+
+
+def pack(x):
+    return T.stack(*x)
+
 # VALUE MANIPULATION
 
 
@@ -367,25 +487,45 @@ def get_value(x):
     return x.get_value()
 
 
+def batch_get_value(xs):
+    '''Returns the value of more than one tensor variable,
+    as a list of Numpy arrays.
+    '''
+    return [get_value(x) for x in xs]
+
+
 def set_value(x, value):
     x.set_value(np.asarray(value, dtype=x.dtype))
 
 
+def batch_set_value(tuples):
+    for x, value in tuples:
+        x.set_value(np.asarray(value, dtype=x.dtype))
+
+
 # GRAPH MANIPULATION
 
 class Function(object):
 
     def __init__(self, inputs, outputs, updates=[], **kwargs):
         self.function = theano.function(inputs, outputs, updates=updates,
-                                        allow_input_downcast=True, **kwargs)
+                                        allow_input_downcast=True,
+                                        on_unused_input='warn',
+                                        **kwargs)
 
     def __call__(self, inputs):
         assert type(inputs) in {list, tuple}
         return self.function(*inputs)
 
 
-def function(inputs, outputs, updates=[]):
-    return Function(inputs, outputs, updates=updates)
+def function(inputs, outputs, updates=[], **kwargs):
+    if len(kwargs) > 0:
+        function_args = inspect.getargspec(theano.function)[0]
+        for key in kwargs.keys():
+            if key not in function_args:
+                msg = "Invalid argument '%s' passed to K.function" % key
+                raise ValueError(msg)
+    return Function(inputs, outputs, updates=updates, **kwargs)
 
 
 def gradients(loss, variables):
@@ -395,90 +535,158 @@ def gradients(loss, variables):
 # CONTROL FLOW
 
 def rnn(step_function, inputs, initial_states,
-        go_backwards=False, mask=None):
+        go_backwards=False, mask=None, constants=None,
+        unroll=False, input_length=None):
     '''Iterates over the time dimension of a tensor.
 
-    Parameters
-    ----------
-    inputs: tensor of temporal data of shape (samples, time, ...)
-        (at least 3D).
-    step_function:
-        Parameters:
-            input: tensor with shape (samples, ...) (no time dimension),
-                representing input for the batch of samples at a certain
-                time step.
-            states: list of tensors.
-        Returns:
-            output: tensor with shape (samples, ...) (no time dimension),
-            new_states: list of tensors, same length and shapes
-                as 'states'.
-    initial_states: tensor with shape (samples, ...) (no time dimension),
-        containing the initial values for the states used in
-        the step function.
-    go_backwards: boolean. If True, do the iteration over
-        the time dimension in reverse order.
-    mask: binary tensor with shape (samples, time),
-        with a zero for every element that is masked.
+    # Arguments
+        inputs: tensor of temporal data of shape (samples, time, ...)
+            (at least 3D).
+        step_function:
+            Parameters:
+                input: tensor with shape (samples, ...) (no time dimension),
+                    representing input for the batch of samples at a certain
+                    time step.
+                states: list of tensors.
+            Returns:
+                output: tensor with shape (samples, ...) (no time dimension),
+                new_states: list of tensors, same length and shapes
+                    as 'states'.
+        initial_states: tensor with shape (samples, ...) (no time dimension),
+            containing the initial values for the states used in
+            the step function.
+        go_backwards: boolean. If True, do the iteration over
+            the time dimension in reverse order.
+        mask: binary tensor with shape (samples, time),
+            with a zero for every element that is masked.
+        constants: a list of constant values passed at each step.
+        unroll: whether to unroll the RNN or to use a symbolic loop (`scan`).
+        input_length: must be specified if using `unroll`.
 
-    Returns
-    -------
-    A tuple (last_output, outputs, new_states).
-        last_output: the latest output of the rnn, of shape (samples, ...)
-        outputs: tensor with shape (samples, time, ...) where each
-            entry outputs[s, t] is the output of the step function
-            at time t for sample s.
-        new_states: list of tensors, latest states returned by
-            the step function, of shape (samples, ...).
+    # Returns
+        A tuple (last_output, outputs, new_states).
+            last_output: the latest output of the rnn, of shape (samples, ...)
+            outputs: tensor with shape (samples, time, ...) where each
+                entry outputs[s, t] is the output of the step function
+                at time t for sample s.
+            new_states: list of tensors, latest states returned by
+                the step function, of shape (samples, ...).
     '''
     ndim = inputs.ndim
     assert ndim >= 3, 'Input should be at least 3D.'
 
+    if unroll:
+        if input_length is None:
+            raise Exception('When specifying `unroll=True`, an `input_length` '
+                            'must be provided to `rnn`.')
+
     axes = [1, 0] + list(range(2, ndim))
     inputs = inputs.dimshuffle(axes)
 
+    if constants is None:
+        constants = []
+
     if mask is not None:
         if mask.ndim == ndim-1:
             mask = expand_dims(mask)
         assert mask.ndim == ndim
         mask = mask.dimshuffle(axes)
 
-        # build an all-zero tensor of shape (samples, output_dim)
-        initial_output = step_function(inputs[0], initial_states)[0] * 0
-        # Theano gets confused by broadcasting patterns in the scan op
-        initial_output = T.unbroadcast(initial_output, 0, 1)
+        if unroll:
+            indices = list(range(input_length))
+            if go_backwards:
+                indices = indices[::-1]
 
-        def _step(input, mask, output_tm1, *states):
-            output, new_states = step_function(input, states)
-            # output previous output if masked.
-            output = T.switch(mask, output, output_tm1)
-            return_states = []
-            for state, new_state in zip(states, new_states):
-                return_states.append(T.switch(mask, new_state, state))
-            return [output] + return_states
+            successive_outputs = []
+            successive_states = []
+            states = initial_states
+            for i in indices:
+                output, new_states = step_function(inputs[i], states + constants)
 
-        results, _ = theano.scan(
-            _step,
-            sequences=[inputs, mask],
-            outputs_info=[initial_output] + initial_states,
-            go_backwards=go_backwards)
+                if len(successive_outputs) == 0:
+                    prev_output = zeros_like(output)
+                else:
+                    prev_output = successive_outputs[-1]
+
+                output = T.switch(mask[i], output, prev_output)
+                kept_states = []
+                for state, new_state in zip(states, new_states):
+                    kept_states.append(T.switch(mask[i], new_state, state))
+                states = kept_states
+
+                successive_outputs.append(output)
+                successive_states.append(states)
+
+            outputs = T.stack(*successive_outputs)
+            states = []
+            for i in range(len(successive_states[-1])):
+                states.append(T.stack(*[states_at_step[i] for states_at_step in successive_states]))
+        else:
+            # build an all-zero tensor of shape (samples, output_dim)
+            initial_output = step_function(inputs[0], initial_states + constants)[0] * 0
+            # Theano gets confused by broadcasting patterns in the scan op
+            initial_output = T.unbroadcast(initial_output, 0, 1)
+
+            def _step(input, mask, output_tm1, *states):
+                output, new_states = step_function(input, states)
+                # output previous output if masked.
+                output = T.switch(mask, output, output_tm1)
+                return_states = []
+                for state, new_state in zip(states, new_states):
+                    return_states.append(T.switch(mask, new_state, state))
+                return [output] + return_states
+
+            results, _ = theano.scan(
+                _step,
+                sequences=[inputs, mask],
+                outputs_info=[initial_output] + initial_states,
+                non_sequences=constants,
+                go_backwards=go_backwards)
+
+            # deal with Theano API inconsistency
+            if type(results) is list:
+                outputs = results[0]
+                states = results[1:]
+            else:
+                outputs = results
+                states = []
     else:
-        def _step(input, *states):
-            output, new_states = step_function(input, states)
-            return [output] + new_states
+        if unroll:
+            indices = list(range(input_length))
+            if go_backwards:
+                indices = indices[::-1]
 
-        results, _ = theano.scan(
-            _step,
-            sequences=inputs,
-            outputs_info=[None] + initial_states,
-            go_backwards=go_backwards)
+            successive_outputs = []
+            successive_states = []
+            states = initial_states
+            for i in indices:
+                output, states = step_function(inputs[i], states + constants)
+                successive_outputs.append(output)
+                successive_states.append(states)
+            outputs = T.stack(*successive_outputs)
+            states = []
+            for i in range(len(successive_states[-1])):
+                states.append(T.stack(*[states_at_step[i] for states_at_step in successive_states]))
 
-    # deal with Theano API inconsistency
-    if type(results) is list:
-        outputs = results[0]
-        states = results[1:]
-    else:
-        outputs = results
-        states = []
+        else:
+            def _step(input, *states):
+                output, new_states = step_function(input, states)
+                return [output] + new_states
+
+            results, _ = theano.scan(
+                _step,
+                sequences=inputs,
+                outputs_info=[None] + initial_states,
+                non_sequences=constants,
+                go_backwards=go_backwards)
+
+            # deal with Theano API inconsistency
+            if type(results) is list:
+                outputs = results[0]
+                states = results[1:]
+            else:
+                outputs = results
+                states = []
 
     outputs = T.squeeze(outputs)
     last_output = outputs[-1]
@@ -495,6 +703,18 @@ def switch(condition, then_expression, else_expression):
     return T.switch(condition, then_expression, else_expression)
 
 
+def in_train_phase(x, alt):
+    x = T.switch(_LEARNING_PHASE, x, alt)
+    x._uses_learning_phase = True
+    return x
+
+
+def in_test_phase(x, alt):
+    x = T.switch(_LEARNING_PHASE, alt, x)
+    x._uses_learning_phase = True
+    return x
+
+
 # NN OPERATIONS
 
 def relu(x, alpha=0., max_value=None):
@@ -516,6 +736,10 @@ def softplus(x):
     return T.nnet.softplus(x)
 
 
+def softsign(x):
+    return T_softsign(x)
+
+
 def categorical_crossentropy(output, target, from_logits=False):
     if from_logits:
         output = T.nnet.softmax(output)
@@ -527,6 +751,13 @@ def categorical_crossentropy(output, target, from_logits=False):
     return T.nnet.categorical_crossentropy(output, target)
 
 
+def sparse_categorical_crossentropy(output, target, from_logits=False):
+    target = T.cast(T.flatten(target), 'int32')
+    target = T.extra_ops.to_one_hot(target, nb_class=output.shape[-1])
+    target = reshape(target, shape(output))
+    return categorical_crossentropy(output, target, from_logits)
+
+
 def binary_crossentropy(output, target, from_logits=False):
     if from_logits:
         output = T.nnet.sigmoid(output)
@@ -569,7 +800,6 @@ def l2_normalize(x, axis):
 def conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='th',
            image_shape=None, filter_shape=None):
     '''
-    Run on cuDNN if available.
     border_mode: string, "same" or "valid".
     '''
     if dim_ordering not in {'th', 'tf'}:
@@ -591,51 +821,151 @@ def conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='th',
             filter_shape = (filter_shape[3], filter_shape[2],
                             filter_shape[0], filter_shape[1])
 
-    if _on_gpu() and dnn.dnn_available():
-        if border_mode == 'same':
-            assert(strides == (1, 1))
-            conv_out = dnn.dnn_conv(img=x,
-                                    kerns=kernel,
-                                    border_mode='full')
-            np_kernel = kernel.eval()
-            shift_x = (np_kernel.shape[2] - 1) // 2
-            shift_y = (np_kernel.shape[3] - 1) // 2
-            conv_out = conv_out[:, :,
-                                shift_x:x.shape[2] + shift_x,
-                                shift_y:x.shape[3] + shift_y]
-        else:
-            conv_out = dnn.dnn_conv(img=x,
-                                    kerns=kernel,
-                                    border_mode=border_mode,
-                                    subsample=strides)
+    if border_mode == 'same':
+        th_border_mode = 'half'
+        np_kernel = kernel.eval()
+    elif border_mode == 'valid':
+        th_border_mode = 'valid'
     else:
-        if border_mode == 'same':
-            th_border_mode = 'full'
-            assert(strides == (1, 1))
-        elif border_mode == 'valid':
-            th_border_mode = 'valid'
-        else:
-            raise Exception('Border mode not supported: ' + str(border_mode))
+        raise Exception('Border mode not supported: ' + str(border_mode))
+
+    # Theano might not accept long type
+    def int_or_none(value):
+        try:
+            return int(value)
+        except TypeError:
+            return None
+
+    if image_shape is not None:
+        image_shape = tuple(int_or_none(v) for v in image_shape)
+
+    if filter_shape is not None:
+        filter_shape = tuple(int_or_none(v) for v in filter_shape)
+
+    conv_out = T.nnet.conv2d(x, kernel,
+                             border_mode=th_border_mode,
+                             subsample=strides,
+                             input_shape=image_shape,
+                             filter_shape=filter_shape)
+
+    if border_mode == 'same':
+        if np_kernel.shape[2] % 2 == 0:
+            conv_out = conv_out[:, :, :(x.shape[2] + strides[0] - 1) // strides[0], :]
+        if np_kernel.shape[3] % 2 == 0:
+            conv_out = conv_out[:, :, :, :(x.shape[3] + strides[1] - 1) // strides[1]]
 
-        conv_out = T.nnet.conv.conv2d(x, kernel,
-                                      border_mode=th_border_mode,
-                                      subsample=strides,
-                                      image_shape=image_shape,
-                                      filter_shape=filter_shape)
-        if border_mode == 'same':
-            np_kernel = kernel.eval()
-            shift_x = (np_kernel.shape[2] - 1) // 2
-            shift_y = (np_kernel.shape[3] - 1) // 2
-            conv_out = conv_out[:, :,
-                                shift_x:x.shape[2] + shift_x,
-                                shift_y:x.shape[3] + shift_y]
     if dim_ordering == 'tf':
         conv_out = conv_out.dimshuffle((0, 2, 3, 1))
     return conv_out
 
 
+def conv3d(x, kernel, strides=(1, 1, 1),
+           border_mode='valid', dim_ordering='th',
+           volume_shape=None, filter_shape=None):
+    '''
+    Run on cuDNN if available.
+    border_mode: string, "same" or "valid".
+    '''
+    if dim_ordering not in {'th', 'tf'}:
+        raise Exception('Unknown dim_ordering ' + str(dim_ordering))
+
+    if border_mode not in {'same', 'valid'}:
+        raise Exception('Invalid border mode: ' + str(border_mode))
+
+    if dim_ordering == 'tf':
+        # TF uses the last dimension as channel dimension,
+        # instead of the 2nd one.
+        # TH input shape: (samples, input_depth, conv_dim1, conv_dim2, conv_dim3)
+        # TF input shape: (samples, conv_dim1, conv_dim2, conv_dim3, input_depth)
+        # TH kernel shape: (out_depth, input_depth, kernel_dim1, kernel_dim2, kernel_dim3)
+        # TF kernel shape: (kernel_dim1, kernel_dim2, kernel_dim3, input_depth, out_depth)
+        x = x.dimshuffle((0, 4, 1, 2, 3))
+        kernel = kernel.dimshuffle((4, 3, 0, 1, 2))
+        if volume_shape:
+            volume_shape = (volume_shape[0], volume_shape[4],
+                            volume_shape[1], volume_shape[2], volume_shape[3])
+        if filter_shape:
+            filter_shape = (filter_shape[4], filter_shape[3],
+                            filter_shape[0], filter_shape[1], filter_shape[2])
+
+    if border_mode == 'same':
+        assert(strides == (1, 1, 1))
+        pad_dim1 = (kernel.shape[2] - 1)
+        pad_dim2 = (kernel.shape[3] - 1)
+        pad_dim3 = (kernel.shape[4] - 1)
+        output_shape = (x.shape[0], x.shape[1],
+                        x.shape[2] + pad_dim1,
+                        x.shape[3] + pad_dim2,
+                        x.shape[4] + pad_dim3)
+        output = T.zeros(output_shape)
+        indices = (slice(None), slice(None),
+                   slice(pad_dim1 // 2, x.shape[2] + pad_dim1 // 2),
+                   slice(pad_dim2 // 2, x.shape[3] + pad_dim2 // 2),
+                   slice(pad_dim3 // 2, x.shape[4] + pad_dim3 // 2))
+        x = T.set_subtensor(output[indices], x)
+        border_mode = 'valid'
+
+    border_mode_3d = (border_mode, border_mode, border_mode)
+    conv_out = conv3d2d.conv3d(signals=x.dimshuffle(0, 2, 1, 3, 4),
+                               filters=kernel.dimshuffle(0, 2, 1, 3, 4),
+                               border_mode=border_mode_3d)
+    conv_out = conv_out.dimshuffle(0, 2, 1, 3, 4)
+
+    # support strides by manually slicing the output
+    if strides != (1, 1, 1):
+        conv_out = conv_out[:, :, ::strides[0], ::strides[1], ::strides[2]]
+
+    if dim_ordering == 'tf':
+        conv_out = conv_out.dimshuffle((0, 2, 3, 4, 1))
+
+    return conv_out
+
+
 def pool2d(x, pool_size, strides=(1, 1), border_mode='valid',
            dim_ordering='th', pool_mode='max'):
+    if border_mode == 'same':
+        w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
+        h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
+        padding = (w_pad, h_pad)
+    elif border_mode == 'valid':
+        padding = (0, 0)
+    else:
+        raise Exception('Invalid border mode: ' + str(border_mode))
+
+    if dim_ordering not in {'th', 'tf'}:
+        raise Exception('Unknown dim_ordering ' + str(dim_ordering))
+
+    if dim_ordering == 'tf':
+        x = x.dimshuffle((0, 3, 1, 2))
+
+    if pool_mode == 'max':
+        pool_out = pool.pool_2d(x, ds=pool_size, st=strides,
+                                ignore_border=True,
+                                padding=padding,
+                                mode='max')
+    elif pool_mode == 'avg':
+        pool_out = pool.pool_2d(x, ds=pool_size, st=strides,
+                                ignore_border=True,
+                                padding=padding,
+                                mode='average_exc_pad')
+    else:
+        raise Exception('Invalid pooling mode: ' + str(pool_mode))
+
+    if border_mode == 'same':
+        expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
+        expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
+
+        pool_out = pool_out[:, :,
+                            : expected_width,
+                            : expected_height]
+
+    if dim_ordering == 'tf':
+        pool_out = pool_out.dimshuffle((0, 2, 3, 1))
+    return pool_out
+
+
+def pool3d(x, pool_size, strides=(1, 1, 1), border_mode='valid',
+           dim_ordering='th', pool_mode='max'):
     if border_mode == 'same':
         # TODO: add implementation for border_mode="same"
         raise Exception('border_mode="same" not supported with Theano.')
@@ -649,23 +979,46 @@ def pool2d(x, pool_size, strides=(1, 1), border_mode='valid',
         raise Exception('Unknown dim_ordering ' + str(dim_ordering))
 
     if dim_ordering == 'tf':
-        x = x.dimshuffle((0, 3, 1, 2))
+        x = x.dimshuffle((0, 4, 1, 2, 3))
 
     if pool_mode == 'max':
-        pool_out = downsample.max_pool_2d(x, ds=pool_size, st=strides,
-                                          ignore_border=ignore_border,
-                                          padding=padding,
-                                          mode='max')
+        # pooling over conv_dim2, conv_dim1 (last two channels)
+        output = pool.pool_2d(input=x.dimshuffle(0, 1, 4, 3, 2),
+                              ds=(pool_size[1], pool_size[0]),
+                              st=(strides[1], strides[0]),
+                              ignore_border=ignore_border,
+                              padding=padding,
+                              mode='max')
+
+        # pooling over conv_dim3
+        pool_out = pool.pool_2d(input=output.dimshuffle(0, 1, 4, 3, 2),
+                                ds=(1, pool_size[2]),
+                                st=(1, strides[2]),
+                                ignore_border=ignore_border,
+                                padding=padding,
+                                mode='max')
+
     elif pool_mode == 'avg':
-        pool_out = downsample.max_pool_2d(x, ds=pool_size, st=strides,
-                                          ignore_border=ignore_border,
-                                          padding=padding,
-                                          mode='average_exc_pad')
+        # pooling over conv_dim2, conv_dim1 (last two channels)
+        output = pool.pool_2d(input=x.dimshuffle(0, 1, 4, 3, 2),
+                              ds=(pool_size[1], pool_size[0]),
+                              st=(strides[1], strides[0]),
+                              ignore_border=ignore_border,
+                              padding=padding,
+                              mode='average_exc_pad')
+
+        # pooling over conv_dim3
+        pool_out = pool.pool_2d(input=output.dimshuffle(0, 1, 4, 3, 2),
+                                ds=(1, pool_size[2]),
+                                st=(1, strides[2]),
+                                ignore_border=ignore_border,
+                                padding=padding,
+                                mode='average_exc_pad')
     else:
         raise Exception('Invalid pooling mode: ' + str(pool_mode))
 
     if dim_ordering == 'tf':
-        pool_out = pool_out.dimshuffle((0, 2, 3, 1))
+        pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
     return pool_out
 
 
@@ -685,9 +1038,9 @@ def random_uniform(shape, low=0.0, high=1.0, dtype=_FLOATX, seed=None):
     rng = RandomStreams(seed=seed)
     return rng.uniform(shape, low=low, high=high, dtype=dtype)
 
-'''
-more TODO:
 
-tensordot -> soon to be introduced in TF
-batched_tensordot -> reimplement
-'''
+def random_binomial(shape, p=0.0, dtype=_FLOATX, seed=None):
+    if seed is None:
+        seed = np.random.randint(10e6)
+    rng = RandomStreams(seed=seed)
+    return rng.binomial(shape, p=p, dtype=dtype)

keras/callbacks.py

@@ -60,8 +60,7 @@ class CallbackList(object):
             callback.on_batch_end(batch, logs)
         self._delta_ts_batch_end.append(time.time() - t_before_callbacks)
         delta_t_median = np.median(self._delta_ts_batch_end)
-        if self._delta_t_batch > 0. and delta_t_median > 0.95 * \
-           self._delta_t_batch and delta_t_median > 0.1:
+        if self._delta_t_batch > 0. and (delta_t_median > 0.95 * self._delta_t_batch and delta_t_median > 0.1):
             warnings.warn('Method on_batch_end() is slow compared '
                           'to the batch update (%f). Check your callbacks.'
                           % delta_t_median)
@@ -92,7 +91,8 @@ class Callback(object):
     will include the following quantities in the `logs` that
     it passes to its callbacks:
 
-        on_epoch_end: logs optionally include `val_loss`
+        on_epoch_end: logs include `acc` and `loss`, and
+            optionally include `val_loss`
             (if validation is enabled in `fit`), and `val_acc`
             (if validation and accuracy monitoring are enabled).
         on_batch_begin: logs include `size`,
@@ -129,11 +129,35 @@ class Callback(object):
 
 
 class BaseLogger(Callback):
-    '''Callback that prints events to the standard output.
+    '''Callback that accumulates epoch averages of
+    the metrics being monitored.
 
     This callback is automatically applied to
-    every Keras model (it is the basis of the verbosity modes
-    in models).
+    every Keras model.
+    '''
+    def on_epoch_begin(self, epoch, logs={}):
+        self.seen = 0
+        self.totals = {}
+
+    def on_batch_end(self, batch, logs={}):
+        batch_size = logs.get('size', 0)
+        self.seen += batch_size
+
+        for k, v in logs.items():
+            if k in self.totals:
+                self.totals[k] += v * batch_size
+            else:
+                self.totals[k] = v * batch_size
+
+    def on_epoch_end(self, epoch, logs={}):
+        for k in self.params['metrics']:
+            if k in self.totals:
+                # make value available to next callbacks
+                logs[k] = self.totals[k] / self.seen
+
+
+class ProgbarLogger(Callback):
+    '''Callback that prints metrics to stdout.
     '''
     def on_train_begin(self, logs={}):
         self.verbose = self.params['verbose']
@@ -145,7 +169,6 @@ class BaseLogger(Callback):
             self.progbar = Progbar(target=self.params['nb_sample'],
                                    verbose=self.verbose)
         self.seen = 0
-        self.totals = {}
 
     def on_batch_begin(self, batch, logs={}):
         if self.seen < self.params['nb_sample']:
@@ -155,11 +178,6 @@ class BaseLogger(Callback):
         batch_size = logs.get('size', 0)
         self.seen += batch_size
 
-        for k, v in logs.items():
-            if k in self.totals:
-                self.totals[k] += v * batch_size
-            else:
-                self.totals[k] = v * batch_size
         for k in self.params['metrics']:
             if k in logs:
                 self.log_values.append((k, logs[k]))
@@ -171,8 +189,6 @@ class BaseLogger(Callback):
 
     def on_epoch_end(self, epoch, logs={}):
         for k in self.params['metrics']:
-            if k in self.totals:
-                self.log_values.append((k, self.totals[k] / self.seen))
             if k in logs:
                 self.log_values.append((k, logs[k]))
         if self.verbose:
@@ -191,26 +207,8 @@ class History(Callback):
         self.epoch = []
         self.history = {}
 
-    def on_epoch_begin(self, epoch, logs={}):
-        self.seen = 0
-        self.totals = {}
-
-    def on_batch_end(self, batch, logs={}):
-        batch_size = logs.get('size', 0)
-        self.seen += batch_size
-        for k, v in logs.items():
-            if k in self.totals:
-                self.totals[k] += v * batch_size
-            else:
-                self.totals[k] = v * batch_size
-
     def on_epoch_end(self, epoch, logs={}):
         self.epoch.append(epoch)
-        for k, v in self.totals.items():
-            if k not in self.history:
-                self.history[k] = []
-            self.history[k].append(v / self.seen)
-
         for k, v in logs.items():
             if k not in self.history:
                 self.history[k] = []
@@ -256,7 +254,7 @@ class ModelCheckpoint(Callback):
 
         if mode not in ['auto', 'min', 'max']:
             warnings.warn('ModelCheckpoint mode %s is unknown, '
-                          'fallback to auto mode.' % (self.mode),
+                          'fallback to auto mode.' % (mode),
                           RuntimeWarning)
             mode = 'auto'
 
@@ -373,26 +371,10 @@ class RemoteMonitor(Callback):
     def __init__(self, root='http://localhost:9000'):
         self.root = root
 
-    def on_epoch_begin(self, epoch, logs={}):
-        self.seen = 0
-        self.totals = {}
-
-    def on_batch_end(self, batch, logs={}):
-        batch_size = logs.get('size', 0)
-        self.seen += batch_size
-        for k, v in logs.items():
-            if k in self.totals:
-                self.totals[k] += v * batch_size
-            else:
-                self.totals[k] = v * batch_size
-
     def on_epoch_end(self, epoch, logs={}):
         import requests
         send = {}
         send['epoch'] = epoch
-
-        for k, v in self.totals.items():
-            send[k] = v / self.seen
         for k, v in logs.items():
             send[k] = v
 
@@ -448,8 +430,11 @@ class TensorBoard(Callback):
         histogram_freq: frequency (in epochs) at which to compute activation
             histograms for the layers of the model. If set to 0,
             histograms won't be computed.
+        write_graph: whether to visualize the graph in tensorboard. The log file can
+            become quite large when write_graph is set to True.
     '''
-    def __init__(self, log_dir='./logs', histogram_freq=0):
+
+    def __init__(self, log_dir='./logs', histogram_freq=0, write_graph=True):
         super(Callback, self).__init__()
         if K._BACKEND != 'tensorflow':
             raise Exception('TensorBoard callback only works '
@@ -457,67 +442,56 @@ class TensorBoard(Callback):
         self.log_dir = log_dir
         self.histogram_freq = histogram_freq
         self.merged = None
+        self.write_graph = write_graph
 
     def _set_model(self, model):
         import tensorflow as tf
         import keras.backend.tensorflow_backend as KTF
 
         self.model = model
-        self.sess = KTF._get_session()
-        if self.histogram_freq and not self.merged:
-            mod_type = self.model.get_config()['name']
-            if mod_type == 'Sequential':
-                layers = {l.get_config()['name']: l for l in self.model.layers}
-            elif mod_type == 'Graph':
-                layers = self.model.nodes
-            else:
-                raise Exception('Unrecognized model:',
-                                self.model.get_config()['name'])
-            for l in layers:
-                cur_layer = layers[l]
-                if hasattr(cur_layer, 'W'):
-                    tf.histogram_summary('{}_W'.format(l), cur_layer.W)
-                if hasattr(cur_layer, 'b'):
-                    tf.histogram_summary('{}_b'.format(l), cur_layer.b)
-                if hasattr(cur_layer, 'get_output'):
-                    tf.histogram_summary('{}_out'.format(l),
-                                         cur_layer.get_output())
+        self.sess = KTF.get_session()
+        if self.histogram_freq and self.merged is None:
+            layers = self.model.layers
+            for layer in layers:
+                if hasattr(layer, 'W'):
+                    tf.histogram_summary('{}_W'.format(layer), layer.W)
+                if hasattr(layer, 'b'):
+                    tf.histogram_summary('{}_b'.format(layer), layer.b)
+                if hasattr(layer, 'output'):
+                    tf.histogram_summary('{}_out'.format(layer),
+                                         layer.output)
         self.merged = tf.merge_all_summaries()
-        self.writer = tf.train.SummaryWriter(self.log_dir,
-                                             self.sess.graph_def)
-
-    def on_epoch_begin(self, epoch, logs={}):
-        self.seen = 0
-        self.totals = {}
-
-    def on_batch_end(self, batch, logs={}):
-        batch_size = logs.get('size', 0)
-        self.seen += batch_size
-        for k, v in logs.items():
-            if k in self.totals:
-                self.totals[k] += v * batch_size
+        if self.write_graph:
+            tf_version = tuple(int(i) for i in tf.__version__.split('.'))
+            if tf_version >= (0, 8, 0):
+                self.writer = tf.train.SummaryWriter(self.log_dir,
+                                                     self.sess.graph)
             else:
-                self.totals[k] = v * batch_size
+                self.writer = tf.train.SummaryWriter(self.log_dir,
+                                                     self.sess.graph_def)
+        else:
+            self.writer = tf.train.SummaryWriter(self.log_dir)
 
     def on_epoch_end(self, epoch, logs={}):
         import tensorflow as tf
 
         if self.model.validation_data and self.histogram_freq:
             if epoch % self.histogram_freq == 0:
-                if self.params.get('show_accuracy'):
-                    test_function = self.model._test_with_acc
+                # TODO: implement batched calls to sess.run
+                # (current call will likely go OOM on GPU)
+                if self.model.uses_learning_phase:
+                    cut_v_data = len(self.model.inputs)
+                    val_data = self.model.validation_data[:cut_v_data] + [0]
+                    tensors = self.model.inputs + [K.learning_phase()]
                 else:
-                    test_function = self.model._test
-                names = [v.name for v in test_function.inputs]
-                feed_dict = dict(zip(names, self.model.validation_data))
+                    val_data = self.model.validation_data
+                    tensors = self.model.inputs
+                feed_dict = dict(zip(tensors, val_data))
                 result = self.sess.run([self.merged], feed_dict=feed_dict)
                 summary_str = result[0]
                 self.writer.add_summary(summary_str, epoch)
 
-        all_values = self.totals.copy()
-        all_values.update(logs)
-
-        for name, value in all_values.items():
+        for name, value in logs.items():
             if name in ['batch', 'size']:
                 continue
             summary = tf.Summary()

keras/constraints.py

@@ -7,7 +7,7 @@ class Constraint(object):
         return p
 
     def get_config(self):
-        return {"name": self.__class__.__name__}
+        return {'name': self.__class__.__name__}
 
 
 class MaxNorm(Constraint):
@@ -42,9 +42,9 @@ class MaxNorm(Constraint):
         return p
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "m": self.m,
-                "axis": self.axis}
+        return {'name': self.__class__.__name__,
+                'm': self.m,
+                'axis': self.axis}
 
 
 class NonNeg(Constraint):
@@ -79,17 +79,15 @@ class UnitNorm(Constraint):
         return p / (K.epsilon() + K.sqrt(K.sum(K.square(p), axis=self.axis, keepdims=True)))
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "axis": self.axis}
+        return {'name': self.__class__.__name__,
+                'axis': self.axis}
 
 
-identity = Constraint
 maxnorm = MaxNorm
 nonneg = NonNeg
 unitnorm = UnitNorm
 
 from .utils.generic_utils import get_from_module
-
-
 def get(identifier, kwargs=None):
-    return get_from_module(identifier, globals(), 'constraint', instantiate=True, kwargs=kwargs)
+    return get_from_module(identifier, globals(), 'constraint',
+                           instantiate=True, kwargs=kwargs)

keras/datasets/cifar.py

@@ -2,7 +2,7 @@
 from __future__ import absolute_import
 import sys
 from six.moves import cPickle
-from six.moves import range
+
 
 def load_batch(fpath, label_key='labels'):
     f = open(fpath, 'rb')

keras/datasets/cifar10.py

@@ -1,6 +1,6 @@
 from __future__ import absolute_import
 from .cifar import load_batch
-from .data_utils import get_file
+from ..utils.data_utils import get_file
 import numpy as np
 import os
 

keras/datasets/cifar100.py

@@ -1,6 +1,6 @@
 from __future__ import absolute_import
 from .cifar import load_batch
-from .data_utils import get_file
+from ..utils.data_utils import get_file
 import numpy as np
 import os
 

keras/datasets/data_utils.py

@@ -1,53 +1,4 @@
-from __future__ import absolute_import
-from __future__ import print_function
+from ..utils.data_utils import *
+import warnings
 
-import tarfile
-import os
-from six.moves.urllib.request import FancyURLopener
-
-from ..utils.generic_utils import Progbar
-
-
-class ParanoidURLopener(FancyURLopener):
-    def http_error_default(self, url, fp, errcode, errmsg, headers):
-        raise Exception('URL fetch failure on {}: {} -- {}'.format(url, errcode, errmsg))
-
-
-def get_file(fname, origin, untar=False):
-    datadir_base = os.path.expanduser(os.path.join('~', '.keras'))
-    if not os.access(datadir_base, os.W_OK):
-        datadir_base = os.path.join('/tmp', '.keras')
-    datadir = os.path.join(datadir_base, 'datasets')
-    if not os.path.exists(datadir):
-        os.makedirs(datadir)
-
-    if untar:
-        untar_fpath = os.path.join(datadir, fname)
-        fpath = untar_fpath + '.tar.gz'
-    else:
-        fpath = os.path.join(datadir, fname)
-
-    if not os.path.exists(fpath):
-        print('Downloading data from',  origin)
-        global progbar
-        progbar = None
-
-        def dl_progress(count, block_size, total_size):
-            global progbar
-            if progbar is None:
-                progbar = Progbar(total_size)
-            else:
-                progbar.update(count*block_size)
-
-        ParanoidURLopener().retrieve(origin, fpath, dl_progress)
-        progbar = None
-
-    if untar:
-        if not os.path.exists(untar_fpath):
-            print('Untaring file...')
-            tfile = tarfile.open(fpath, 'r:gz')
-            tfile.extractall(path=datadir)
-            tfile.close()
-        return untar_fpath
-
-    return fpath
+warnings.warn('data_utils has been moved to keras.utils.data_utils.')

keras/datasets/imdb.py

@@ -1,7 +1,7 @@
 from __future__ import absolute_import
 from six.moves import cPickle
 import gzip
-from .data_utils import get_file
+from ..utils.data_utils import get_file
 from six.moves import zip
 import numpy as np
 
@@ -60,10 +60,10 @@ def load_data(path="imdb.pkl", nb_words=None, skip_top=0,
             nX.append(nx)
         X = nX
 
-    X_train = X[:int(len(X) * (1 - test_split))]
-    y_train = labels[:int(len(X) * (1 - test_split))]
+    X_train = np.array(X[:int(len(X) * (1 - test_split))])
+    y_train = np.array(labels[:int(len(X) * (1 - test_split))])
 
-    X_test = X[int(len(X) * (1 - test_split)):]
-    y_test = labels[int(len(X) * (1 - test_split)):]
+    X_test = np.array(X[int(len(X) * (1 - test_split)):])
+    y_test = np.array(labels[int(len(X) * (1 - test_split)):])
 
     return (X_train, y_train), (X_test, y_test)

keras/datasets/mnist.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 import gzip
-from .data_utils import get_file
+from ..utils.data_utils import get_file
 from six.moves import cPickle
 import sys
 

keras/datasets/reuters.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
-from .data_utils import get_file
+from ..utils.data_utils import get_file
 from six.moves import cPickle
 from six.moves import zip
 import numpy as np

keras/engine/__init__.py

@@ -0,0 +1,10 @@
+# note: topology.Node is an internal class,
+# it isn't meant to be used by Keras users.
+from .topology import InputSpec
+from .topology import Input
+from .topology import InputLayer
+from .topology import Layer
+from .topology import Merge
+from .topology import merge
+from .topology import get_source_inputs
+from .training import Model

keras/initializations.py

@@ -3,9 +3,26 @@ import numpy as np
 from . import backend as K
 
 
-def get_fans(shape):
-    fan_in = shape[0] if len(shape) == 2 else np.prod(shape[1:])
-    fan_out = shape[1] if len(shape) == 2 else shape[0]
+def get_fans(shape, dim_ordering='th'):
+    if len(shape) == 2:
+        fan_in = shape[0]
+        fan_out = shape[1]
+    elif len(shape) == 4 or len(shape) == 5:
+        # assuming convolution kernels (2D or 3D).
+        # TH kernel shape: (depth, input_depth, ...)
+        # TF kernel shape: (..., input_depth, depth)
+        if dim_ordering == 'th':
+            fan_in = np.prod(shape[1:])
+            fan_out = shape[0]
+        elif dim_ordering == 'tf':
+            fan_in = np.prod(shape[:-1])
+            fan_out = shape[-1]
+        else:
+            raise Exception('Invalid dim_ordering: ' + dim_ordering)
+    else:
+        # no specific assumptions
+        fan_in = np.sqrt(np.prod(shape))
+        fan_out = np.sqrt(np.prod(shape))
     return fan_in, fan_out
 
 
@@ -19,39 +36,39 @@ def normal(shape, scale=0.05, name=None):
                       name=name)
 
 
-def lecun_uniform(shape, name=None):
+def lecun_uniform(shape, name=None, dim_ordering='th'):
     ''' Reference: LeCun 98, Efficient Backprop
         http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf
     '''
-    fan_in, fan_out = get_fans(shape)
+    fan_in, fan_out = get_fans(shape, dim_ordering=dim_ordering)
     scale = np.sqrt(3. / fan_in)
     return uniform(shape, scale, name=name)
 
 
-def glorot_normal(shape, name=None):
+def glorot_normal(shape, name=None, dim_ordering='th'):
     ''' Reference: Glorot & Bengio, AISTATS 2010
     '''
-    fan_in, fan_out = get_fans(shape)
+    fan_in, fan_out = get_fans(shape, dim_ordering=dim_ordering)
     s = np.sqrt(2. / (fan_in + fan_out))
     return normal(shape, s, name=name)
 
 
-def glorot_uniform(shape, name=None):
-    fan_in, fan_out = get_fans(shape)
+def glorot_uniform(shape, name=None, dim_ordering='th'):
+    fan_in, fan_out = get_fans(shape, dim_ordering=dim_ordering)
     s = np.sqrt(6. / (fan_in + fan_out))
     return uniform(shape, s, name=name)
 
 
-def he_normal(shape, name=None):
+def he_normal(shape, name=None, dim_ordering='th'):
     ''' Reference:  He et al., http://arxiv.org/abs/1502.01852
     '''
-    fan_in, fan_out = get_fans(shape)
+    fan_in, fan_out = get_fans(shape, dim_ordering=dim_ordering)
     s = np.sqrt(2. / fan_in)
     return normal(shape, s, name=name)
 
 
-def he_uniform(shape, name=None):
-    fan_in, fan_out = get_fans(shape)
+def he_uniform(shape, name=None, dim_ordering='th'):
+    fan_in, fan_out = get_fans(shape, dim_ordering=dim_ordering)
     s = np.sqrt(6. / fan_in)
     return uniform(shape, s, name=name)
 
@@ -85,5 +102,6 @@ def one(shape, name=None):
 
 
 from .utils.generic_utils import get_from_module
-def get(identifier):
-    return get_from_module(identifier, globals(), 'initialization')
+def get(identifier, **kwargs):
+    return get_from_module(identifier, globals(),
+                           'initialization', kwargs=kwargs)

keras/layers/__init__.py

@@ -1,4 +1,5 @@
 from __future__ import absolute_import
+from ..engine import Layer, Input, InputLayer, Merge, merge, InputSpec
 from .core import *
 from .convolutional import *
 from .recurrent import *
@@ -6,3 +7,4 @@ from .normalization import *
 from .embeddings import *
 from .noise import *
 from .advanced_activations import *
+from .wrappers import *

keras/layers/advanced_activations.py

@@ -1,13 +1,14 @@
 from .. import initializations
-from ..layers.core import MaskedLayer
+from ..engine import Layer
 from .. import backend as K
 import numpy as np
 
 
-class LeakyReLU(MaskedLayer):
+class LeakyReLU(Layer):
     '''Special version of a Rectified Linear Unit
     that allows a small gradient when the unit is not active:
-    `f(x) = alpha*x for x < 0`.
+    `f(x) = alpha * x for x < 0`,
+    `f(x) = x for x >= 0`.
 
     # Input shape
         Arbitrary. Use the keyword argument `input_shape`
@@ -21,22 +22,25 @@ class LeakyReLU(MaskedLayer):
         alpha: float >= 0. Negative slope coefficient.
     '''
     def __init__(self, alpha=0.3, **kwargs):
-        super(LeakyReLU, self).__init__(**kwargs)
+        self.supports_masking = True
         self.alpha = alpha
+        super(LeakyReLU, self).__init__(**kwargs)
 
-    def get_output(self, train):
-        X = self.get_input(train)
-        return K.relu(X, alpha=self.alpha)
+    def call(self, x, mask=None):
+        return K.relu(x, alpha=self.alpha)
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "alpha": self.alpha}
+        config = {'alpha': self.alpha}
         base_config = super(LeakyReLU, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
 
 
-class PReLU(MaskedLayer):
-    '''
+class PReLU(Layer):
+    '''Parametric Rectified Linear Unit:
+    `f(x) = alphas * x for x < 0`,
+    `f(x) = x for x >= 0`,
+    where `alphas` is a learned array with the same shape as x.
+
     # Input shape
         Arbitrary. Use the keyword argument `input_shape`
         (tuple of integers, does not include the samples axis)
@@ -45,42 +49,44 @@ class PReLU(MaskedLayer):
     # Output shape
         Same shape as the input.
 
-    # Arguments:
+    # Arguments
         init: initialization function for the weights.
         weights: initial weights, as a list of a single numpy array.
 
-    # References:
+    # References
         - [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](http://arxiv.org/pdf/1502.01852v1.pdf)
     '''
     def __init__(self, init='zero', weights=None, **kwargs):
+        self.supports_masking = True
         self.init = initializations.get(init)
         self.initial_weights = weights
         super(PReLU, self).__init__(**kwargs)
 
-    def build(self):
-        input_shape = self.input_shape[1:]
-        self.alphas = self.init(input_shape)
+    def build(self, input_shape):
+        self.alphas = self.init(input_shape[1:],
+                                name='{}_alphas'.format(self.name))
         self.trainable_weights = [self.alphas]
 
         if self.initial_weights is not None:
             self.set_weights(self.initial_weights)
             del self.initial_weights
 
-    def get_output(self, train):
-        X = self.get_input(train)
-        pos = K.relu(X)
-        neg = self.alphas * (X - abs(X)) * 0.5
+    def call(self, x, mask=None):
+        pos = K.relu(x)
+        neg = self.alphas * (x - abs(x)) * 0.5
         return pos + neg
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "init": self.init.__name__}
+        config = {'init': self.init.__name__}
         base_config = super(PReLU, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
 
 
-class ELU(MaskedLayer):
-    '''
+class ELU(Layer):
+    '''Exponential Linear Unit:
+    `f(x) =  alpha * (exp(x) - 1.) for x < 0`,
+    `f(x) = x for x >= 0`.
+
     # Input shape
         Arbitrary. Use the keyword argument `input_shape`
         (tuple of integers, does not include the samples axis)
@@ -96,24 +102,24 @@ class ELU(MaskedLayer):
         - [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](http://arxiv.org/pdf/1511.07289v1.pdf)
     '''
     def __init__(self, alpha=1.0, **kwargs):
+        self.supports_masking = True
+        self.alpha = K.cast_to_floatx(alpha)
         super(ELU, self).__init__(**kwargs)
-        self.alpha = alpha
 
-    def get_output(self, train):
-        X = self.get_input(train)
-        pos = K.relu(X)
-        neg = (X - abs(X)) * 0.5
+    def call(self, x, mask=None):
+        pos = K.relu(x)
+        neg = (x - abs(x)) * 0.5
         return pos + self.alpha * (K.exp(neg) - 1.)
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "alpha": self.alpha}
+        config = {'alpha': self.alpha}
         base_config = super(ELU, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
 
 
-class ParametricSoftplus(MaskedLayer):
-    '''Parametric Softplus of the form: alpha * log(1 + exp(beta * X))
+class ParametricSoftplus(Layer):
+    '''Parametric Softplus:
+    `alpha * log(1 + exp(beta * x))`
 
     # Input shape
         Arbitrary. Use the keyword argument `input_shape`
@@ -128,40 +134,43 @@ class ParametricSoftplus(MaskedLayer):
         beta_init: float. Initial values of the beta weights.
         weights: initial weights, as a list of 2 numpy arrays.
 
-    # References:
+    # References
         - [Inferring Nonlinear Neuronal Computation Based on Physiologically Plausible Inputs](http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1003143)
     '''
     def __init__(self, alpha_init=0.2, beta_init=5.0,
                  weights=None, **kwargs):
-        self.alpha_init = alpha_init
-        self.beta_init = beta_init
+        self.supports_masking = True
+        self.alpha_init = K.cast_to_floatx(alpha_init)
+        self.beta_init = K.cast_to_floatx(beta_init)
         self.initial_weights = weights
         super(ParametricSoftplus, self).__init__(**kwargs)
 
-    def build(self):
-        input_shape = self.input_shape[1:]
-        self.alphas = K.variable(self.alpha_init * np.ones(input_shape))
-        self.betas = K.variable(self.beta_init * np.ones(input_shape))
+    def build(self, input_shape):
+        input_shape = input_shape[1:]
+        self.alphas = K.variable(self.alpha_init * np.ones(input_shape),
+                                 name='{}_alphas'.format(self.name))
+        self.betas = K.variable(self.beta_init * np.ones(input_shape),
+                                name='{}_betas'.format(self.name))
         self.trainable_weights = [self.alphas, self.betas]
 
         if self.initial_weights is not None:
             self.set_weights(self.initial_weights)
             del self.initial_weights
 
-    def get_output(self, train):
-        X = self.get_input(train)
-        return K.softplus(self.betas * X) * self.alphas
+    def call(self, x, mask=None):
+        return K.softplus(self.betas * x) * self.alphas
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "alpha_init": self.alpha_init,
-                  "beta_init": self.beta_init}
+        config = {'alpha_init': self.alpha_init,
+                  'beta_init': self.beta_init}
         base_config = super(ParametricSoftplus, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
 
 
-class ThresholdedLinear(MaskedLayer):
-    '''Thresholded Linear Activation.
+class ThresholdedReLU(Layer):
+    '''Thresholded Rectified Linear Unit:
+    `f(x) = x for x > theta`
+    `f(x) = 0 otherwise`.
 
     # Input shape
         Arbitrary. Use the keyword argument `input_shape`
@@ -175,50 +184,83 @@ class ThresholdedLinear(MaskedLayer):
         theta: float >= 0. Threshold location of activation.
 
     # References
-        [Zero-Bias Autoencoders and the Benefits of Co-Adapting Features](http://arxiv.org/pdf/1402.3337.pdf)
-    '''
-    def __init__(self, theta=1.0, **kwargs):
-        super(ThresholdedLinear, self).__init__(**kwargs)
-        self.theta = theta
-
-    def get_output(self, train):
-        X = self.get_input(train)
-        return K.switch(K.abs(X) < self.theta, 0, X)
-
-    def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "theta": self.theta}
-        base_config = super(ThresholdedLinear, self).get_config()
-        return dict(list(base_config.items()) + list(config.items()))
-
-
-class ThresholdedReLU(MaskedLayer):
-    '''Thresholded Rectified Activation.
-
-    # Input shape
-        Arbitrary. Use the keyword argument `input_shape`
-        (tuple of integers, does not include the samples axis)
-        when using this layer as the first layer in a model.
-
-    # Output shape
-        Same shape as the input.
-
-    # Arguments
-        theta: float >= 0. Threshold location of activation.
-
-    # References
-        [Zero-Bias Autoencoders and the Benefits of Co-Adapting Features](http://arxiv.org/pdf/1402.3337.pdf)
+        - [Zero-Bias Autoencoders and the Benefits of Co-Adapting Features](http://arxiv.org/pdf/1402.3337.pdf)
     '''
     def __init__(self, theta=1.0, **kwargs):
+        self.supports_masking = True
+        self.theta = K.cast_to_floatx(theta)
         super(ThresholdedReLU, self).__init__(**kwargs)
-        self.theta = theta
 
-    def get_output(self, train):
-        X = self.get_input(train)
-        return K.switch(X > self.theta, X, 0)
+    def call(self, x, mask=None):
+        return x * K.cast(x > self.theta, K.floatx())
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "theta": self.theta}
+        config = {'theta': self.theta}
         base_config = super(ThresholdedReLU, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
+
+
+class SReLU(Layer):
+    '''S-shaped Rectified Linear Unit.
+
+    # Input shape
+        Arbitrary. Use the keyword argument `input_shape`
+        (tuple of integers, does not include the samples axis)
+        when using this layer as the first layer in a model.
+
+    # Output shape
+        Same shape as the input.
+
+    # Arguments
+        t_left_init: initialization function for the left part intercept
+        a_left_init: initialization function for the left part slope
+        t_right_init: initialization function for the right part intercept
+        a_right_init: initialization function for the right part slope
+
+    # References
+        - [Deep Learning with S-shaped Rectified Linear Activation Units](http://arxiv.org/abs/1512.07030)
+    '''
+    def __init__(self, t_left_init='zero', a_left_init='glorot_uniform',
+                 t_right_init='glorot_uniform', a_right_init='one', **kwargs):
+        self.supports_masking = True
+        self.t_left_init = t_left_init
+        self.a_left_init = a_left_init
+        self.t_right_init = t_right_init
+        self.a_right_init = a_right_init
+        super(SReLU, self).__init__(**kwargs)
+
+    def build(self, input_shape):
+        input_shape = input_shape[1:]
+
+        t_left_init = initializations.get(self.t_left_init)
+        a_left_init = initializations.get(self.a_left_init)
+        t_right_init = initializations.get(self.t_right_init)
+        a_right_init = initializations.get(self.a_right_init)
+
+        self.t_left = t_left_init(input_shape,
+                                  name='{}_t_left'.format(self.name))
+        self.a_left = a_left_init(input_shape,
+                                  name='{}_a_left'.format(self.name))
+        self.t_right = t_right_init(input_shape,
+                                    name='{}_t_right'.format(self.name))
+        self.a_right = a_right_init(input_shape,
+                                    name='{}_a_right'.format(self.name))
+        # ensure the the right part is always to the right of the left
+        self.t_right_actual = self.t_left + abs(self.t_right)
+        self.trainable_weights = [self.t_left, self.a_left,
+                                  self.t_right, self.a_right]
+
+    def call(self, x, mask=None):
+        Y_left_and_center = self.t_left + K.relu(x - self.t_left,
+                                                 self.a_left,
+                                                 self.t_right_actual - self.t_left)
+        Y_right = K.relu(x - self.t_right_actual) * self.a_right
+        return Y_left_and_center + Y_right
+
+    def get_config(self):
+        config = {'t_left_init': self.t_left_init,
+                  'a_left_init': self.a_left_init,
+                  't_right_init': self.t_right_init,
+                  'a_right_init': self.a_right_init}
+        base_config = super(SReLU, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))

keras/layers/containers.py

@@ -1,533 +0,0 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import print_function
-
-from collections import OrderedDict
-from .. import backend as K
-from ..layers.core import Layer, Merge, Siamese, SiameseHead
-from six.moves import range
-
-
-class Sequential(Layer):
-    '''The Sequential container is a linear stack of layers.
-    Apart from the `add` methods and the `layers` constructor argument,
-    the API is identical to that of the `Layer` class.
-
-    This class is also the basis for the `keras.models.Sequential` model.
-
-    # Arguments
-        layers: list of layers to be added to the container.
-    '''
-    def __init__(self, layers=[]):
-        self.layers = []
-        self.layer_cache = {}
-        for layer in layers:
-            self.add(layer)
-        self._cache_enabled = True
-
-    def __call__(self, X, mask=None, train=False):
-        # turn off layer cache temporarily
-        tmp_cache_enabled = self.cache_enabled
-        self.cache_enabled = False
-        # recursively search for a layer which is not a Sequential model
-        layer = self
-        while issubclass(layer.__class__, Sequential):
-            layer = layer.layers[0]
-        # set temporary input to first layer
-        tmp_input = layer.get_input
-        tmp_mask = None
-        layer.get_input = lambda _: X
-        if hasattr(layer, 'get_input_mask'):
-            tmp_mask = layer.get_input_mask
-            layer.get_input_mask = lambda _: mask
-        Y = self.get_output(train=train)
-        # return input from first layer to what it was
-        layer.get_input = tmp_input
-        if hasattr(layer, 'get_input_mask'):
-            layer.get_input_mask = tmp_mask
-        self.cache_enabled = tmp_cache_enabled
-        return Y
-
-    @property
-    def cache_enabled(self):
-        return self._cache_enabled
-
-    @cache_enabled.setter
-    def cache_enabled(self, value):
-        self._cache_enabled = value
-        for l in self.layers:
-            l.cache_enabled = value
-
-    def set_previous(self, layer):
-        self.layers[0].previous = layer
-
-    def add(self, layer):
-        layer.layer_cache = self.layer_cache
-        self.layers.append(layer)
-        if len(self.layers) > 1:
-            self.layers[-1].set_previous(self.layers[-2])
-            if not hasattr(self.layers[0], 'input'):
-                self.set_input()
-
-    @property
-    def trainable_weights(self):
-        weights = []
-        for l in self.layers:
-            if l.trainable:
-                weights += l.get_params()[0]
-        return weights
-
-    @property
-    def regularizers(self):
-        regularizers = []
-        for l in self.layers:
-            if l.trainable:
-                regularizers += l.get_params()[1]
-        return regularizers
-
-    @property
-    def constraints(self):
-        constraints = []
-        for l in self.layers:
-            if l.trainable:
-                constraints += l.get_params()[2]
-        return constraints
-
-    @property
-    def updates(self):
-        updates = []
-        for l in self.layers:
-            if l.trainable:
-                updates += l.get_params()[3]
-        return updates
-
-    @property
-    def state_updates(self):
-        """
-        Return the `updates` from all layers in the sequence that are
-        stateful.  This is useful for separating _training_ updates and
-        _prediction_ updates for when we need to update a layers internal state
-        during a stateful prediction.
-        """
-        state_updates = []
-        for l in self.layers:
-            if getattr(l, 'stateful', False):
-                state_updates += l.get_params()[3]
-        return state_updates
-
-    def reset_states(self):
-        for l in self.layers:
-            if hasattr(l, 'reset_states') and getattr(l, 'stateful', False):
-                l.reset_states()
-
-    @property
-    def output_shape(self):
-        return self.layers[-1].output_shape
-
-    def get_output(self, train=False):
-        return self.layers[-1].get_output(train)
-
-    def set_input(self):
-        for l in self.layers:
-            if hasattr(l, 'input'):
-                ndim = K.ndim(l.input)
-                self.layers[0].input = K.placeholder(ndim=ndim)
-                break
-
-    def get_input(self, train=False):
-        if not hasattr(self.layers[0], 'input'):
-            self.set_input()
-        return self.layers[0].get_input(train)
-
-    @property
-    def input_shape(self):
-        return self.layers[0].input_shape
-
-    @property
-    def input(self):
-        return self.get_input()
-
-    def get_weights(self):
-        weights = []
-        for layer in self.layers:
-            weights += layer.get_weights()
-        return weights
-
-    def set_weights(self, weights):
-        for i in range(len(self.layers)):
-            nb_param = len(self.layers[i].trainable_weights) + len(self.layers[i].non_trainable_weights)
-            self.layers[i].set_weights(weights[:nb_param])
-            weights = weights[nb_param:]
-
-    def get_config(self):
-        return {'name': self.__class__.__name__,
-                'layers': [layer.get_config() for layer in self.layers]}
-
-    def count_params(self):
-        return sum([layer.count_params() for layer in self.layers])
-
-
-class Graph(Layer):
-    '''Implement a NN graph with arbitrary layer connections,
-    arbitrary number of inputs and arbitrary number of outputs.
-
-    This class is also the basis for the `keras.models.Graph` model.
-
-    Note: `Graph` can only be used as a layer
-    (connect, input, get_input, get_output)
-    when it has exactly one input and one output.
-    '''
-    def __init__(self):
-        self.namespace = set()  # strings
-        self.nodes = OrderedDict()  # layer-like
-        self.inputs = {}  # layer-like
-        self.input_order = []  # strings
-        self.outputs = {}  # layer-like
-        self.output_order = []  # strings
-        self.input_config = []  # dicts
-        self.output_config = []  # dicts
-        self.node_config = []  # dicts
-        self.layer_cache = {}
-
-    @property
-    def nb_input(self):
-        return len(self.inputs)
-
-    @property
-    def nb_output(self):
-        return len(self.outputs)
-
-    @property
-    def trainable_weights(self):
-        weights = []
-        for l in self.nodes.values():
-            if l.trainable:
-                weights += l.get_params()[0]
-        return weights
-
-    @property
-    def regularizers(self):
-        regularizers = []
-        for l in self.nodes.values():
-            if l.trainable:
-                regularizers += l.get_params()[1]
-        return regularizers
-
-    @property
-    def constraints(self):
-        constraints = []
-        for l in self.nodes.values():
-            if l.trainable:
-                constraints += l.get_params()[2]
-        return constraints
-
-    @property
-    def updates(self):
-        updates = []
-        for l in self.nodes.values():
-            if l.trainable:
-                updates += l.get_params()[3]
-        return updates
-
-    @property
-    def state_updates(self):
-        """
-        Return the `updates` from all nodes in that graph for nodes that are
-        stateful.  This is useful for separating _training_ updates and
-        _prediction_ updates for when we need to update a layers internal state
-        during a stateful prediction.
-        """
-        state_updates = []
-        for l in self.nodes.values():
-            if getattr(l, 'stateful', False):
-                state_updates += l.get_params()[3]
-        return state_updates
-
-    def reset_states(self):
-        for l in self.nodes.values():
-            if hasattr(l, 'reset_states') and getattr(l, 'stateful', False):
-                l.reset_states()
-
-    def set_previous(self, layer, connection_map={}):
-        if self.nb_input != layer.nb_output:
-            raise Exception('Cannot connect layers: '
-                            'input count does not match output count.')
-        if self.nb_input == 1:
-            self.inputs[self.input_order[0]].set_previous(layer)
-        else:
-            if not connection_map:
-                raise Exception('Cannot attach multi-input layer: '
-                                'no connection_map provided.')
-            for k, v in connection_map.items():
-                if k in self.inputs and v in layer.outputs:
-                    self.inputs[k].set_previous(layer.outputs[v])
-                else:
-                    raise Exception('Invalid connection map.')
-
-    def get_input(self, train=False):
-        if len(self.inputs) == len(self.outputs) == 1:
-            return self.inputs[self.input_order[0]].get_input(train)
-        else:
-            return dict([(k, v.get_input(train)) for k, v in self.inputs.items()])
-
-    @property
-    def input(self):
-        return self.get_input()
-
-    @property
-    def output_shape(self):
-        if self.nb_output == 1:
-            # return tuple
-            return self.outputs[self.output_order[0]].output_shape
-        else:
-            # return dictionary mapping output names to shape tuples
-            return dict([(k, v.output_shape) for k, v in self.outputs.items()])
-
-    def get_output(self, train=False):
-        if len(self.inputs) == len(self.outputs) == 1:
-            return self.outputs[self.output_order[0]].get_output(train)
-        else:
-            return dict([(k, v.get_output(train)) for k, v in self.outputs.items()])
-
-    def add_input(self, name, input_shape=None,
-                  batch_input_shape=None, dtype='float'):
-        '''Add an input to the graph.
-
-        # Arguments:
-            name: string. The name of the new input. Must be unique in the graph.
-            input_shape: a tuple of integers, the expected shape of the input samples.
-                Does not include the batch size.
-            batch_input_shape: a tuple of integers, the expected shape of the
-                whole input batch, including the batch size.
-            dtype: 'float' or 'int'.
-        '''
-        if name in self.namespace:
-            raise Exception('Duplicate node identifier: ' + name)
-        self.namespace.add(name)
-        self.input_order.append(name)
-        layer = Layer(name=name)  # empty layer
-        if input_shape:
-            layer.set_input_shape((None,) + tuple(input_shape))
-        elif batch_input_shape:
-            layer.set_input_shape(batch_input_shape)
-        if dtype == 'float':
-            layer.input = K.placeholder(shape=layer.input_shape, name=name)
-        else:
-            if (input_shape and len(input_shape) == 1) or (batch_input_shape and len(batch_input_shape) == 2):
-                layer.input = K.placeholder(shape=layer.input_shape,
-                                            dtype='int32',
-                                            name=name)
-            else:
-                raise Exception('Type "int" can only be used with ndim==2 (Embedding).')
-        self.inputs[name] = layer
-        config = {'name': name, 'dtype': dtype}
-        if batch_input_shape:
-            config['batch_input_shape'] = batch_input_shape
-        else:
-            config['input_shape'] = input_shape
-        self.input_config.append(config)
-
-    def add_node(self, layer, name, input=None, inputs=[],
-                 merge_mode='concat', concat_axis=-1, dot_axes=-1,
-                 create_output=False):
-        '''Add a node in the graph. It can be connected to multiple
-        inputs, which will first be merged into one tensor
-        according to the mode specified.
-
-        # Arguments
-            layer: the layer at the node.
-            name: name for the node.
-            input: when connecting the layer to a single input,
-                this is the name of the incoming node.
-            inputs: when connecting the layer to multiple inputs,
-                this is a list of names of incoming nodes.
-            merge_mode: one of {concat, sum, dot, ave, mul}
-            concat_axis: when `merge_mode=='concat'`, this is the
-                input concatenation axis.
-            dot_axes: when `merge_mode='dot'`, this is the contraction axes
-                specification; see the `Merge layer for details.
-            create_output: boolean. Set this to `True` if you want the output
-                of your node to be an output of the graph.
-        '''
-        if name in self.namespace:
-            raise Exception('Duplicate node identifier: ' + name)
-        layer.name = name
-        if input:
-            if input not in self.namespace:
-                raise Exception('Unknown node/input identifier: ' + input)
-            if input in self.nodes:
-                layer.set_previous(self.nodes[input])
-            elif input in self.inputs:
-                layer.set_previous(self.inputs[input])
-        if inputs:
-            to_merge = []
-            for n in inputs:
-                if n in self.nodes:
-                    to_merge.append(self.nodes[n])
-                elif n in self.inputs:
-                    to_merge.append(self.inputs[n])
-                else:
-                    raise Exception('Unknown identifier: ' + n)
-            merge = Merge(to_merge, mode=merge_mode,
-                          concat_axis=concat_axis, dot_axes=dot_axes)
-            layer.set_previous(merge)
-
-        self.namespace.add(name)
-        layer.layer_cache = self.layer_cache
-        self.nodes[name] = layer
-        self.node_config.append({'name': name,
-                                 'input': input,
-                                 'inputs': inputs,
-                                 'merge_mode': merge_mode,
-                                 'concat_axis': concat_axis,
-                                 'dot_axes': dot_axes,
-                                 'create_output': create_output})
-
-        if create_output:
-            self.add_output(name, input=name)
-
-    def add_shared_node(self, layer, name, inputs=[], merge_mode=None,
-                        concat_axis=-1, dot_axes=-1, outputs=[],
-                        create_output=False):
-        '''Used to share a same layer across multiple nodes.
-
-        Supposed, for instance, that you want to apply one same `Dense`
-        layer after to the output of two different nodes.
-        You can then add the `Dense` layer as a shared node.
-
-        # Arguments
-            layer: The layer to be shared across multiple inputs
-            name: Name of the shared node
-            inputs: List of names of input nodes
-            merge_mode: Same meaning as `merge_mode` argument of `add_node()`
-            concat_axis: Same meaning as `concat_axis` argument of `add_node()`
-            dot_axes: Same meaning as `dot_axes` argument of `add_node()`
-            outputs: Used when `merge_mode=None`. Names for the output nodes.
-            create_output: Same meaning as `create_output` argument of `add_node()`.
-        '''
-        if name in self.namespace:
-            raise Exception('Duplicate node identifier: ' + name)
-        for o in outputs:
-            if o in self.namespace:
-                raise Exception('Duplicate node identifier: ' + o)
-        if merge_mode:
-            if merge_mode not in {'sum', 'ave', 'mul', 'dot', 'cos', 'concat', 'join'}:
-                raise Exception('Invalid merge mode')
-        layers = []
-        for i in range(len(inputs)):
-            input = inputs[i]
-            if input in self.nodes:
-                n = self.nodes[input]
-                if n.__class__.__name__ == 'Siamese':
-                    if n.merge_mode is None:
-                        for j in range(len(n.inputs)):
-                            sh = SiameseHead(j)
-                            sh.previous = n
-                            layers.append(sh)
-                    else:
-                        layers.append(n)
-                else:
-                    layers.append(n)
-            elif input in self.inputs:
-                n = self.inputs[input]
-                layers.append(n)
-            else:
-                raise Exception('Unknown identifier: ' + input)
-        s = Siamese(layer, layers, merge_mode,
-                    concat_axis=concat_axis,
-                    dot_axes=dot_axes,
-                    is_graph=True)
-        self.namespace.add(name)
-        self.nodes[name] = s
-        self.node_config.append({'name': name,
-                                 'inputs': inputs,
-                                 'merge_mode': merge_mode,
-                                 'concat_axis': concat_axis,
-                                 'dot_axes': dot_axes,
-                                 'create_output': create_output if merge_mode else False})
-        if not merge_mode:
-            for i in range(len(outputs)):
-                sh = SiameseHead(i)
-                sh.previous = s
-                sh_name = outputs[i]
-                self.namespace.add(sh_name)
-                self.nodes[sh_name] = sh
-                self.node_config.append({'name': sh_name,
-                                         'inputs': [name],
-                                         'create_output': create_output})
-                if create_output:
-                    self.add_output(sh_name, input=sh_name)
-
-        if create_output and merge_mode:
-            if merge_mode == 'join':
-                raise Exception('Output can not be of type OrderedDict')
-            self.add_output(name, input=name)
-
-    def add_output(self, name, input=None, inputs=[],
-                   merge_mode='concat', concat_axis=-1, dot_axes=-1):
-        '''Add an output to the graph.
-
-        This output can merge several node outputs into a single output.
-
-        # Arguments
-            name: name of the output.
-            input: when connecting the layer to a single input,
-                this is the name of the incoming node.
-            inputs: when connecting the layer to multiple inputs,
-                this is a list of names of incoming nodes.
-            merge_mode: one of {concat, sum, dot, ave, mul}
-            concat_axis: when `merge_mode=='concat'`, this is the
-                input concatenation axis.
-            dot_axes: when `merge_mode='dot'`, this is the contraction axes
-                specification; see the `Merge layer for details.
-        '''
-        if name in self.output_order:
-            raise Exception('Duplicate output identifier: ' + name)
-        if input:
-            if input not in self.namespace:
-                raise Exception('Unknown node/input identifier: ' + input)
-            if input in self.nodes:
-                self.outputs[name] = self.nodes[input]
-            elif input in self.inputs:
-                self.outputs[name] = self.inputs[input]
-        if inputs:
-            to_merge = []
-            for n in inputs:
-                if n not in self.nodes:
-                    raise Exception('Unknown identifier: ' + n)
-                to_merge.append(self.nodes[n])
-            merge = Merge(to_merge, mode=merge_mode,
-                          concat_axis=concat_axis, dot_axes=dot_axes)
-            self.outputs[name] = merge
-
-        self.output_order.append(name)
-        self.output_config.append({'name': name,
-                                   'input': input,
-                                   'inputs': inputs,
-                                   'merge_mode': merge_mode,
-                                   'concat_axis': concat_axis,
-                                   'dot_axes': dot_axes})
-
-    def get_config(self):
-        return {'name': self.__class__.__name__,
-                'input_config': self.input_config,
-                'node_config': self.node_config,
-                'output_config': self.output_config,
-                'input_order': self.input_order,
-                'output_order': self.output_order,
-                'nodes': dict([(c['name'], self.nodes[c['name']].get_config()) for c in self.node_config])}
-
-    def count_params(self):
-        return sum([layer.count_params() for layer in self.nodes.values()])
-
-    def get_weights(self):
-        weights = []
-        for layer in self.nodes.values():
-            weights += layer.get_weights()
-        return weights
-
-    def set_weights(self, weights):
-        for layer in self.nodes.values():
-            nb_param = len(layer.get_weights())
-            layer.set_weights(weights[:nb_param])
-            weights = weights[nb_param:]

keras/layers/embeddings.py

@@ -1,10 +1,8 @@
 from __future__ import absolute_import
+
 from .. import backend as K
-
-from .. import activations, initializations, regularizers, constraints
-from ..layers.core import Layer, MaskedLayer
-
-from ..constraints import unitnorm
+from .. import initializations, regularizers, constraints
+from ..engine import Layer
 
 
 class Embedding(Layer):
@@ -13,14 +11,24 @@ class Embedding(Layer):
 
     This layer can only be used as the first layer in a model.
 
-    # Input shape
-        2D tensor with shape: `(nb_samples, sequence_length)`.
+    # Example
 
-    # Output shape
-        3D tensor with shape: `(nb_samples, sequence_length, output_dim)`.
+    ```python
+      model = Sequential()
+      model.add(Embedding(1000, 64, input_length=10))
+      # the model will take as input an integer matrix of size (batch, input_length).
+      # the largest integer (i.e. word index) in the input should be no larger than 999 (vocabulary size).
+      # now model.output_shape == (None, 10, 64), where None is the batch dimension.
+
+      input_array = np.random.randint(1000, size=(32, 10))
+
+      model.compile('rmsprop', 'mse')
+      output_array = model.predict(input_array)
+      assert output_array.shape == (32, 10, 64)
+    ```
 
     # Arguments
-      input_dim: int >= 0. Size of the vocabulary, ie.
+      input_dim: int > 0. Size of the vocabulary, ie.
           1 + maximum integer index occurring in the input data.
       output_dim: int >= 0. Dimension of the dense embedding.
       init: name of initialization function for the weights
@@ -38,10 +46,22 @@ class Embedding(Layer):
           This is useful for [recurrent layers](recurrent.md) which may take
           variable length input. If this is `True` then all subsequent layers
           in the model need to support masking or an exception will be raised.
+          If mask_zero is set to True, as a consequence, index 0 cannot be
+          used in the vocabulary (input_dim should equal |vocabulary| + 2).
       input_length: Length of input sequences, when it is constant.
           This argument is required if you are going to connect
           `Flatten` then `Dense` layers upstream
           (without it, the shape of the dense outputs cannot be computed).
+      dropout: float between 0 and 1. Fraction of the embeddings to drop.
+
+    # Input shape
+        2D tensor with shape: `(nb_samples, sequence_length)`.
+
+    # Output shape
+        3D tensor with shape: `(nb_samples, sequence_length, output_dim)`.
+
+    # References
+        - [A Theoretically Grounded Application of Dropout in Recurrent Neural Networks](http://arxiv.org/abs/1512.05287)
     '''
     input_ndim = 2
 
@@ -50,28 +70,35 @@ class Embedding(Layer):
                  W_regularizer=None, activity_regularizer=None,
                  W_constraint=None,
                  mask_zero=False,
-                 weights=None, **kwargs):
+                 weights=None, dropout=0., **kwargs):
         self.input_dim = input_dim
         self.output_dim = output_dim
         self.init = initializations.get(init)
         self.input_length = input_length
         self.mask_zero = mask_zero
+        self.dropout = dropout
 
         self.W_constraint = constraints.get(W_constraint)
-        self.constraints = [self.W_constraint]
 
         self.W_regularizer = regularizers.get(W_regularizer)
         self.activity_regularizer = regularizers.get(activity_regularizer)
 
+        if 0. < self.dropout < 1.:
+            self.uses_learning_phase = True
         self.initial_weights = weights
-        kwargs['input_shape'] = (self.input_dim,)
+        kwargs['input_shape'] = (self.input_length,)
+        kwargs['input_dtype'] = 'int32'
         super(Embedding, self).__init__(**kwargs)
 
-    def build(self):
-        self.input = K.placeholder(shape=(self.input_shape[0], self.input_length),
-                                   dtype='int32')
-        self.W = self.init((self.input_dim, self.output_dim))
+    def build(self, input_shape):
+        self.W = self.init((self.input_dim, self.output_dim),
+                           name='{}_W'.format(self.name))
         self.trainable_weights = [self.W]
+
+        self.constraints = {}
+        if self.W_constraint:
+            self.constraints[self.W] = self.W_constraint
+
         self.regularizers = []
         if self.W_regularizer:
             self.W_regularizer.set_param(self.W)
@@ -84,31 +111,39 @@ class Embedding(Layer):
         if self.initial_weights is not None:
             self.set_weights(self.initial_weights)
 
-    def get_output_mask(self, train=None):
-        X = self.get_input(train)
+    def compute_mask(self, x, mask=None):
         if not self.mask_zero:
             return None
         else:
-            return K.not_equal(X, 0)
+            return K.not_equal(x, 0)
 
-    @property
-    def output_shape(self):
-        return (self.input_shape[0], self.input_length, self.output_dim)
+    def get_output_shape_for(self, input_shape):
+        if not self.input_length:
+            input_length = input_shape[1]
+        else:
+            input_length = self.input_length
+        return (input_shape[0], input_length, self.output_dim)
 
-    def get_output(self, train=False):
-        X = self.get_input(train)
-        out = K.gather(self.W, X)
+    def call(self, x, mask=None):
+        if 0. < self.dropout < 1.:
+            retain_p = 1. - self.dropout
+            B = K.random_binomial((self.input_dim,), p=retain_p) * (1. / retain_p)
+            B = K.expand_dims(B)
+            W = K.in_train_phase(self.W * B, self.W)
+        else:
+            W = self.W
+        out = K.gather(W, x)
         return out
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "input_dim": self.input_dim,
-                  "output_dim": self.output_dim,
-                  "init": self.init.__name__,
-                  "input_length": self.input_length,
-                  "mask_zero": self.mask_zero,
-                  "activity_regularizer": self.activity_regularizer.get_config() if self.activity_regularizer else None,
-                  "W_regularizer": self.W_regularizer.get_config() if self.W_regularizer else None,
-                  "W_constraint": self.W_constraint.get_config() if self.W_constraint else None}
+        config = {'input_dim': self.input_dim,
+                  'output_dim': self.output_dim,
+                  'init': self.init.__name__,
+                  'input_length': self.input_length,
+                  'mask_zero': self.mask_zero,
+                  'activity_regularizer': self.activity_regularizer.get_config() if self.activity_regularizer else None,
+                  'W_regularizer': self.W_regularizer.get_config() if self.W_regularizer else None,
+                  'W_constraint': self.W_constraint.get_config() if self.W_constraint else None,
+                  'dropout': self.dropout}
         base_config = super(Embedding, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))

keras/layers/noise.py

@@ -1,9 +1,9 @@
 from __future__ import absolute_import
-from .core import MaskedLayer
+from ..engine import Layer
 from .. import backend as K
 
 
-class GaussianNoise(MaskedLayer):
+class GaussianNoise(Layer):
     '''Apply to the input an additive zero-centred gaussian noise with
     standard deviation `sigma`. This is useful to mitigate overfitting
     (you could see it as a kind of random data augmentation).
@@ -12,6 +12,44 @@ class GaussianNoise(MaskedLayer):
 
     As it is a regularization layer, it is only active at training time.
 
+    # Arguments
+        sigma: float, standard deviation of the noise distribution.
+
+    # Input shape
+        Arbitrary. Use the keyword argument `input_shape`
+        (tuple of integers, does not include the samples axis)
+        when using this layer as the first layer in a model.
+
+    # Output shape
+        Same shape as input.
+    '''
+    def __init__(self, sigma, **kwargs):
+        self.supports_masking = True
+        self.sigma = sigma
+        self.uses_learning_phase = True
+        super(GaussianNoise, self).__init__(**kwargs)
+
+    def call(self, x, mask=None):
+        noise_x = x + K.random_normal(shape=K.shape(x),
+                                      mean=0.,
+                                      std=self.sigma)
+        return K.in_train_phase(noise_x, x)
+
+    def get_config(self):
+        config = {'sigma': self.sigma}
+        base_config = super(GaussianNoise, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))
+
+
+class GaussianDropout(Layer):
+    '''Apply to the input an multiplicative one-centred gaussian noise
+    with standard deviation `sqrt(p/(1-p))`.
+
+    As it is a regularization layer, it is only active at training time.
+
+    # Arguments
+        p: float, drop probability (as with `Dropout`).
+
     # Input shape
         Arbitrary. Use the keyword argument `input_shape`
         (tuple of integers, does not include the samples axis)
@@ -20,56 +58,24 @@ class GaussianNoise(MaskedLayer):
     # Output shape
         Same shape as input.
 
-    # Arguments
-        sigma: float, standard deviation of the noise distribution.
-    '''
-    def __init__(self, sigma, **kwargs):
-        super(GaussianNoise, self).__init__(**kwargs)
-        self.sigma = sigma
-
-    def get_output(self, train=False):
-        X = self.get_input(train)
-        if not train or self.sigma == 0:
-            return X
-        else:
-            return X + K.random_normal(shape=K.shape(X),
-                                       mean=0.,
-                                       std=self.sigma)
-
-    def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "sigma": self.sigma}
-        base_config = super(GaussianNoise, self).get_config()
-        return dict(list(base_config.items()) + list(config.items()))
-
-
-class GaussianDropout(MaskedLayer):
-    '''Apply to the input an multiplicative one-centred gaussian noise
-    with standard deviation `sqrt(p/(1-p))`.
-
-    As it is a regularization layer, it is only active at training time.
-
-    # Arguments
-        p: float, drop probability (as with `Dropout`).
-
-    # References:
+    # References
         [Dropout: A Simple Way to Prevent Neural Networks from Overfitting Srivastava, Hinton, et al. 2014](http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf)
     '''
     def __init__(self, p, **kwargs):
-        super(GaussianDropout, self).__init__(**kwargs)
+        self.supports_masking = True
         self.p = p
+        if 0 < p < 1:
+            self.uses_learning_phase = True
+        super(GaussianDropout, self).__init__(**kwargs)
 
-    def get_output(self, train):
-        X = self.get_input(train)
-        if train:
-            # self.p refers to drop probability rather than
-            # retain probability (as in paper), for consistency
-            X *= K.random_normal(shape=K.shape(X), mean=1.0,
-                                 std=K.sqrt(self.p / (1.0 - self.p)))
-        return X
+    def call(self, x, mask=None):
+        if 0 < self.p < 1:
+            noise_x = x * K.random_normal(shape=K.shape(x), mean=1.0,
+                                          std=K.sqrt(self.p / (1.0 - self.p)))
+            return K.in_train_phase(noise_x, x)
+        return x
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "p": self.p}
+        config = {'p': self.p}
         base_config = super(GaussianDropout, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))

keras/layers/normalization.py

@@ -1,4 +1,4 @@
-from ..layers.core import Layer
+from ..engine import Layer, InputSpec
 from .. import initializations
 from .. import backend as K
 
@@ -8,14 +8,6 @@ class BatchNormalization(Layer):
     i.e. applies a transformation that maintains the mean activation
     close to 0 and the activation standard deviation close to 1.
 
-    # Input shape
-        Arbitrary. Use the keyword argument `input_shape`
-        (tuple of integers, does not include the samples axis)
-        when using this layer as the first layer in a model.
-
-    # Output shape
-        Same shape as input.
-
     # Arguments
         epsilon: small float > 0. Fuzz parameter.
         mode: integer, 0 or 1.
@@ -37,71 +29,96 @@ class BatchNormalization(Layer):
         weights: Initialization weights.
             List of 2 numpy arrays, with shapes:
             `[(input_shape,), (input_shape,)]`
+        beta_init: name of initialization function for shift parameter
+            (see [initializations](../initializations.md)), or alternatively,
+            Theano/TensorFlow function to use for weights initialization.
+            This parameter is only relevant if you don't pass a `weights` argument.
+        gamma_init: name of initialization function for scale parameter (see
+            [initializations](../initializations.md)), or alternatively,
+            Theano/TensorFlow function to use for weights initialization.
+            This parameter is only relevant if you don't pass a `weights` argument.
+
+    # Input shape
+        Arbitrary. Use the keyword argument `input_shape`
+        (tuple of integers, does not include the samples axis)
+        when using this layer as the first layer in a model.
+
+    # Output shape
+        Same shape as input.
 
     # References
-        - [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](http://arxiv.org/pdf/1502.03167v3.pdf)
+        - [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](http://jmlr.org/proceedings/papers/v37/ioffe15.html)
     '''
     def __init__(self, epsilon=1e-6, mode=0, axis=-1, momentum=0.9,
-                 weights=None, **kwargs):
-        self.init = initializations.get("uniform")
+                 weights=None, beta_init='zero', gamma_init='one', **kwargs):
+        self.beta_init = initializations.get(beta_init)
+        self.gamma_init = initializations.get(gamma_init)
         self.epsilon = epsilon
         self.mode = mode
         self.axis = axis
         self.momentum = momentum
         self.initial_weights = weights
+        self.uses_learning_phase = True
         super(BatchNormalization, self).__init__(**kwargs)
 
-    def build(self):
-        input_shape = self.input_shape  # starts with samples axis
+    def build(self, input_shape):
+        self.input_spec = [InputSpec(shape=input_shape)]
         shape = (input_shape[self.axis],)
 
-        self.gamma = self.init(shape)
-        self.beta = K.zeros(shape)
+        self.gamma = self.gamma_init(shape, name='{}_gamma'.format(self.name))
+        self.beta = self.beta_init(shape, name='{}_beta'.format(self.name))
         self.trainable_weights = [self.gamma, self.beta]
 
-        self.running_mean = K.zeros(shape)
-        self.running_std = K.ones(shape)
+        self.running_mean = K.zeros(shape,
+                                    name='{}_running_mean'.format(self.name))
+        self.running_std = K.ones(shape,
+                                  name='{}_running_std'.format(self.name))
         self.non_trainable_weights = [self.running_mean, self.running_std]
 
         if self.initial_weights is not None:
             self.set_weights(self.initial_weights)
             del self.initial_weights
 
-    def get_output(self, train):
-        X = self.get_input(train)
+    def call(self, x, mask=None):
         if self.mode == 0:
-            input_shape = self.input_shape
+            input_shape = self.input_spec[0].shape
+
             reduction_axes = list(range(len(input_shape)))
             del reduction_axes[self.axis]
             broadcast_shape = [1] * len(input_shape)
             broadcast_shape[self.axis] = input_shape[self.axis]
-            if train:
-                m = K.mean(X, axis=reduction_axes)
-                brodcast_m = K.reshape(m, broadcast_shape)
-                std = K.mean(K.square(X - brodcast_m) + self.epsilon, axis=reduction_axes)
-                std = K.sqrt(std)
-                brodcast_std = K.reshape(std, broadcast_shape)
-                mean_update = self.momentum * self.running_mean + (1-self.momentum) * m
-                std_update = self.momentum * self.running_std + (1-self.momentum) * std
-                self.updates = [(self.running_mean, mean_update),
-                                (self.running_std, std_update)]
-                X_normed = (X - brodcast_m) / (brodcast_std + self.epsilon)
-            else:
-                brodcast_m = K.reshape(self.running_mean, broadcast_shape)
-                brodcast_std = K.reshape(self.running_std, broadcast_shape)
-                X_normed = ((X - brodcast_m) /
-                            (brodcast_std + self.epsilon))
-            out = K.reshape(self.gamma, broadcast_shape) * X_normed + K.reshape(self.beta, broadcast_shape)
+
+            # case: train mode (uses stats of the current batch)
+            mean = K.mean(x, axis=reduction_axes)
+            brodcast_mean = K.reshape(mean, broadcast_shape)
+            std = K.mean(K.square(x - brodcast_mean) + self.epsilon, axis=reduction_axes)
+            std = K.sqrt(std)
+            brodcast_std = K.reshape(std, broadcast_shape)
+            mean_update = self.momentum * self.running_mean + (1 - self.momentum) * mean
+            std_update = self.momentum * self.running_std + (1 - self.momentum) * std
+            self.updates = [(self.running_mean, mean_update),
+                            (self.running_std, std_update)]
+            x_normed = (x - brodcast_mean) / (brodcast_std + self.epsilon)
+
+            # case: test mode (uses running averages)
+            brodcast_running_mean = K.reshape(self.running_mean, broadcast_shape)
+            brodcast_running_std = K.reshape(self.running_std, broadcast_shape)
+            x_normed_running = ((x - brodcast_running_mean) / (brodcast_running_std + self.epsilon))
+
+            # pick the normalized form of x corresponding to the training phase
+            x_normed = K.in_train_phase(x_normed, x_normed_running)
+            out = K.reshape(self.gamma, broadcast_shape) * x_normed + K.reshape(self.beta, broadcast_shape)
+
         elif self.mode == 1:
-            m = K.mean(X, axis=-1, keepdims=True)
-            std = K.std(X, axis=-1, keepdims=True)
-            X_normed = (X - m) / (std + self.epsilon)
-            out = self.gamma * X_normed + self.beta
+            # sample-wise normalization
+            m = K.mean(x, axis=-1, keepdims=True)
+            std = K.std(x, axis=-1, keepdims=True)
+            x_normed = (x - m) / (std + self.epsilon)
+            out = self.gamma * x_normed + self.beta
         return out
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "epsilon": self.epsilon,
+        config = {"epsilon": self.epsilon,
                   "mode": self.mode,
                   "axis": self.axis,
                   "momentum": self.momentum}

keras/layers/recurrent.py

@@ -3,25 +3,67 @@ from __future__ import absolute_import
 import numpy as np
 
 from .. import backend as K
-from .. import activations, initializations
-from ..layers.core import MaskedLayer
+from .. import activations, initializations, regularizers
+from ..engine import Layer, InputSpec
 
 
-class Recurrent(MaskedLayer):
+def time_distributed_dense(x, w, b=None, dropout=None,
+                           input_dim=None, output_dim=None, timesteps=None):
+    '''Apply y.w + b for every temporal slice y of x.
+    '''
+    if not input_dim:
+        # won't work with TensorFlow
+        input_dim = K.shape(x)[2]
+    if not timesteps:
+        # won't work with TensorFlow
+        timesteps = K.shape(x)[1]
+    if not output_dim:
+        # won't work with TensorFlow
+        output_dim = K.shape(w)[1]
+
+    if dropout is not None and 0. < dropout < 1.:
+        # apply the same dropout pattern at every timestep
+        ones = K.ones_like(K.reshape(x[:, 0, :], (-1, input_dim)))
+        dropout_matrix = K.dropout(ones, dropout)
+        expanded_dropout_matrix = K.repeat(dropout_matrix, timesteps)
+        x = K.in_train_phase(x * expanded_dropout_matrix, x)
+
+    # collapse time dimension and batch dimension together
+    x = K.reshape(x, (-1, input_dim))
+
+    x = K.dot(x, w)
+    if b:
+        x = x + b
+    # reshape to 3D tensor
+    x = K.reshape(x, (-1, timesteps, output_dim))
+    return x
+
+
+class Recurrent(Layer):
     '''Abstract base class for recurrent layers.
-    Do not use in a model -- it's not a functional layer!
+    Do not use in a model -- it's not a valid layer!
+    Use its children classes `LSTM`, `GRU` and `SimpleRNN` instead.
 
-    All recurrent layers (GRU, LSTM, SimpleRNN) also
+    All recurrent layers (`LSTM`, `GRU`, `SimpleRNN`) also
     follow the specifications of this class and accept
     the keyword arguments listed below.
 
-    # Input shape
-        3D tensor with shape `(nb_samples, timesteps, input_dim)`.
+    # Example
 
-    # Output shape
-        - if `return_sequences`: 3D tensor with shape
-            `(nb_samples, timesteps, output_dim)`.
-        - else, 2D tensor with shape `(nb_samples, output_dim)`.
+    ```python
+        # as the first layer in a Sequential model
+        model = Sequential()
+        model.add(LSTM(32, input_shape=(10, 64)))
+        # now model.output_shape == (None, 10, 32)
+        # note: `None` is the batch dimension.
+
+        # the following is identical:
+        model = Sequential()
+        model.add(LSTM(32, input_dim=64, input_length=10))
+
+        # for subsequent layers, not need to specify the input size:
+        model.add(LSTM(16))
+    ```
 
     # Arguments
         weights: list of numpy arrays to set as initial weights.
@@ -34,6 +76,25 @@ class Recurrent(MaskedLayer):
         stateful: Boolean (default False). If True, the last state
             for each sample at index i in a batch will be used as initial
             state for the sample of index i in the following batch.
+        unroll: Boolean (default False). If True, the network will be unrolled,
+            else a symbolic loop will be used. When using TensorFlow, the network
+            is always unrolled, so this argument does not do anything.
+            Unrolling can speed-up a RNN, although it tends to be more memory-intensive.
+            Unrolling is only suitable for short sequences.
+        consume_less: one of "cpu", "mem", or "gpu" (LSTM/GRU only).
+            If set to "cpu", the RNN will use
+            an implementation that uses fewer, larger matrix products,
+            thus running faster on CPU but consuming more memory.
+
+            If set to "mem", the RNN will use more matrix products,
+            but smaller ones, thus running slower (may actually be faster on GPU)
+            while consuming less memory.
+
+            If set to "gpu" (LSTM/GRU only), the RNN will combine the input gate,
+            the forget gate and the output gate into a single matrix,
+            enabling more time-efficient parallelization on the GPU. Note: RNN
+            dropout must be shared for all gates, resulting in a slightly
+            reduced regularization.
         input_dim: dimensionality of the input (integer).
             This argument (or alternatively, the keyword argument `input_shape`)
             is required when using this layer as the first layer in a model.
@@ -47,6 +108,14 @@ class Recurrent(MaskedLayer):
             at the level of the first layer
             (e.g. via the `input_shape` argument)
 
+    # Input shape
+        3D tensor with shape `(nb_samples, timesteps, input_dim)`.
+
+    # Output shape
+        - if `return_sequences`: 3D tensor with shape
+            `(nb_samples, timesteps, output_dim)`.
+        - else, 2D tensor with shape `(nb_samples, output_dim)`.
+
     # Masking
         This layer supports masking for input data with a variable number
         of timesteps. To introduce masks to your data,
@@ -78,75 +147,92 @@ class Recurrent(MaskedLayer):
 
         To reset the states of your model, call `.reset_states()` on either
         a specific layer, or on your entire model.
-    '''
-    input_ndim = 3
 
+    # Note on using dropout with TensorFlow
+        When using the TensorFlow backend, specify a fixed batch size for your model
+        following the notes on statefulness RNNs.
+    '''
     def __init__(self, weights=None,
                  return_sequences=False, go_backwards=False, stateful=False,
+                 unroll=False, consume_less='cpu',
                  input_dim=None, input_length=None, **kwargs):
         self.return_sequences = return_sequences
         self.initial_weights = weights
         self.go_backwards = go_backwards
         self.stateful = stateful
+        self.unroll = unroll
+        self.consume_less = consume_less
 
+        self.supports_masking = True
+        self.input_spec = [InputSpec(ndim=3)]
         self.input_dim = input_dim
         self.input_length = input_length
         if self.input_dim:
             kwargs['input_shape'] = (self.input_length, self.input_dim)
         super(Recurrent, self).__init__(**kwargs)
 
-    def get_output_mask(self, train=False):
-        if self.return_sequences:
-            return super(Recurrent, self).get_output_mask(train)
-        else:
-            return None
-
-    @property
-    def output_shape(self):
-        input_shape = self.input_shape
+    def get_output_shape_for(self, input_shape):
         if self.return_sequences:
             return (input_shape[0], input_shape[1], self.output_dim)
         else:
             return (input_shape[0], self.output_dim)
 
+    def compute_mask(self, input, mask):
+        if self.return_sequences:
+            return mask
+        else:
+            return None
+
     def step(self, x, states):
         raise NotImplementedError
 
-    def get_initial_states(self, X):
+    def get_constants(self, x):
+        return []
+
+    def get_initial_states(self, x):
         # build an all-zero tensor of shape (samples, output_dim)
-        initial_state = K.zeros_like(X)  # (samples, timesteps, input_dim)
+        initial_state = K.zeros_like(x)  # (samples, timesteps, input_dim)
         initial_state = K.sum(initial_state, axis=1)  # (samples, input_dim)
         reducer = K.zeros((self.input_dim, self.output_dim))
         initial_state = K.dot(initial_state, reducer)  # (samples, output_dim)
         initial_states = [initial_state for _ in range(len(self.states))]
         return initial_states
 
-    def get_output(self, train=False):
-        # input shape: (nb_samples, time (padded with zeros), input_dim)
-        X = self.get_input(train)
-        mask = self.get_input_mask(train)
+    def preprocess_input(self, x):
+        return x
 
-        assert K.ndim(X) == 3
+    def call(self, x, mask=None):
+        # input shape: (nb_samples, time (padded with zeros), input_dim)
+        # note that the .build() method of subclasses MUST define
+        # self.input_spec with a complete input shape.
+        input_shape = self.input_spec[0].shape
         if K._BACKEND == 'tensorflow':
-            if not self.input_shape[1]:
-                raise Exception('When using TensorFlow, you should define ' +
-                                'explicitly the number of timesteps of ' +
-                                'your sequences.\n' +
-                                'If your first layer is an Embedding, ' +
-                                'make sure to pass it an "input_length" ' +
-                                'argument. Otherwise, make sure ' +
-                                'the first layer has ' +
-                                'an "input_shape" or "batch_input_shape" ' +
-                                'argument, including the time axis.')
+            if not input_shape[1]:
+                raise Exception('When using TensorFlow, you should define '
+                                'explicitly the number of timesteps of '
+                                'your sequences.\n'
+                                'If your first layer is an Embedding, '
+                                'make sure to pass it an "input_length" '
+                                'argument. Otherwise, make sure '
+                                'the first layer has '
+                                'an "input_shape" or "batch_input_shape" '
+                                'argument, including the time axis. '
+                                'Found input shape at layer ' + self.name +
+                                ': ' + str(input_shape))
         if self.stateful:
             initial_states = self.states
         else:
-            initial_states = self.get_initial_states(X)
+            initial_states = self.get_initial_states(x)
+        constants = self.get_constants(x)
+        preprocessed_input = self.preprocess_input(x)
 
-        last_output, outputs, states = K.rnn(self.step, X,
+        last_output, outputs, states = K.rnn(self.step, preprocessed_input,
                                              initial_states,
                                              go_backwards=self.go_backwards,
-                                             mask=mask)
+                                             mask=mask,
+                                             constants=constants,
+                                             unroll=self.unroll,
+                                             input_length=input_shape[1])
         if self.stateful:
             self.updates = []
             for i in range(len(states)):
@@ -158,22 +244,23 @@ class Recurrent(MaskedLayer):
             return last_output
 
     def get_config(self):
-        config = {"name": self.__class__.__name__,
-                  "return_sequences": self.return_sequences,
-                  "go_backwards": self.go_backwards,
-                  "stateful": self.stateful}
+        config = {'return_sequences': self.return_sequences,
+                  'go_backwards': self.go_backwards,
+                  'stateful': self.stateful,
+                  'unroll': self.unroll,
+                  'consume_less': self.consume_less}
         if self.stateful:
-            config['batch_input_shape'] = self.input_shape
+            config['batch_input_shape'] = self.input_spec[0].shape
         else:
             config['input_dim'] = self.input_dim
             config['input_length'] = self.input_length
-            
+
         base_config = super(Recurrent, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
 
 
 class SimpleRNN(Recurrent):
-    '''Fully-connected RNN where the output is to fed back to input.
+    '''Fully-connected RNN where the output is to be fed back to input.
 
     # Arguments
         output_dim: dimension of the internal projections and the final output.
@@ -184,18 +271,38 @@ class SimpleRNN(Recurrent):
         activation: activation function.
             Can be the name of an existing function (str),
             or a Theano function (see: [activations](../activations.md)).
+        W_regularizer: instance of [WeightRegularizer](../regularizers.md)
+            (eg. L1 or L2 regularization), applied to the input weights matrices.
+        U_regularizer: instance of [WeightRegularizer](../regularizers.md)
+            (eg. L1 or L2 regularization), applied to the recurrent weights matrices.
+        b_regularizer: instance of [WeightRegularizer](../regularizers.md),
+            applied to the bias.
+        dropout_W: float between 0 and 1. Fraction of the input units to drop for input gates.
+        dropout_U: float between 0 and 1. Fraction of the input units to drop for recurrent connections.
+
+    # References
+        - [A Theoretically Grounded Application of Dropout in Recurrent Neural Networks](http://arxiv.org/abs/1512.05287)
     '''
     def __init__(self, output_dim,
                  init='glorot_uniform', inner_init='orthogonal',
-                 activation='sigmoid', **kwargs):
+                 activation='tanh',
+                 W_regularizer=None, U_regularizer=None, b_regularizer=None,
+                 dropout_W=0., dropout_U=0., **kwargs):
         self.output_dim = output_dim
         self.init = initializations.get(init)
         self.inner_init = initializations.get(inner_init)
         self.activation = activations.get(activation)
+        self.W_regularizer = regularizers.get(W_regularizer)
+        self.U_regularizer = regularizers.get(U_regularizer)
+        self.b_regularizer = regularizers.get(b_regularizer)
+        self.dropout_W, self.dropout_U = dropout_W, dropout_U
+
+        if self.dropout_W or self.dropout_U:
+            self.uses_learning_phase = True
         super(SimpleRNN, self).__init__(**kwargs)
 
-    def build(self):
-        input_shape = self.input_shape
+    def build(self, input_shape):
+        self.input_spec = [InputSpec(shape=input_shape)]
         if self.stateful:
             self.reset_states()
         else:
@@ -204,9 +311,23 @@ class SimpleRNN(Recurrent):
         input_dim = input_shape[2]
         self.input_dim = input_dim
 
-        self.W = self.init((input_dim, self.output_dim))
-        self.U = self.inner_init((self.output_dim, self.output_dim))
-        self.b = K.zeros((self.output_dim,))
+        self.W = self.init((input_dim, self.output_dim),
+                           name='{}_W'.format(self.name))
+        self.U = self.inner_init((self.output_dim, self.output_dim),
+                                 name='{}_U'.format(self.name))
+        self.b = K.zeros((self.output_dim,), name='{}_b'.format(self.name))
+
+        self.regularizers = []
+        if self.W_regularizer:
+            self.W_regularizer.set_param(self.W)
+            self.regularizers.append(self.W_regularizer)
+        if self.U_regularizer:
+            self.U_regularizer.set_param(self.U)
+            self.regularizers.append(self.U_regularizer)
+        if self.b_regularizer:
+            self.b_regularizer.set_param(self.b)
+            self.regularizers.append(self.b_regularizer)
+
         self.trainable_weights = [self.W, self.U, self.b]
 
         if self.initial_weights is not None:
@@ -215,30 +336,70 @@ class SimpleRNN(Recurrent):
 
     def reset_states(self):
         assert self.stateful, 'Layer must be stateful.'
-        input_shape = self.input_shape
+        input_shape = self.input_spec[0].shape
         if not input_shape[0]:
             raise Exception('If a RNN is stateful, a complete ' +
-                            'input_shape must be provided ' +
-                            '(including batch size).')
+                            'input_shape must be provided (including batch size).')
         if hasattr(self, 'states'):
             K.set_value(self.states[0],
                         np.zeros((input_shape[0], self.output_dim)))
         else:
             self.states = [K.zeros((input_shape[0], self.output_dim))]
 
+    def preprocess_input(self, x):
+        if self.consume_less == 'cpu':
+            input_shape = self.input_spec[0].shape
+            input_dim = input_shape[2]
+            timesteps = input_shape[1]
+            return time_distributed_dense(x, self.W, self.b, self.dropout_W,
+                                          input_dim, self.output_dim,
+                                          timesteps)
+        else:
+            return x
+
     def step(self, x, states):
-        # states only contains the previous output.
-        assert len(states) == 1
         prev_output = states[0]
-        h = K.dot(x, self.W) + self.b
-        output = self.activation(h + K.dot(prev_output, self.U))
+        B_U = states[1]
+        B_W = states[2]
+
+        if self.consume_less == 'cpu':
+            h = x
+        else:
+            h = K.dot(x * B_W, self.W) + self.b
+
+        output = self.activation(h + K.dot(prev_output * B_U, self.U))
         return output, [output]
 
+    def get_constants(self, x):
+        constants = []
+        if 0 < self.dropout_U < 1:
+            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
+            ones = K.concatenate([ones] * self.output_dim, 1)
+            B_U = K.in_train_phase(K.dropout(ones, self.dropout_U), ones)
+            constants.append(B_U)
+        else:
+            constants.append(K.cast_to_floatx(1.))
+        if self.consume_less == 'cpu' and 0 < self.dropout_W < 1:
+            input_shape = self.input_spec[0].shape
+            input_dim = input_shape[-1]
+            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
+            ones = K.concatenate([ones] * input_dim, 1)
+            B_W = K.in_train_phase(K.dropout(ones, self.dropout_W), ones)
+            constants.append(B_W)
+        else:
+            constants.append(K.cast_to_floatx(1.))
+        return constants
+
     def get_config(self):
-        config = {"output_dim": self.output_dim,
-                  "init": self.init.__name__,
-                  "inner_init": self.inner_init.__name__,
-                  "activation": self.activation.__name__}
+        config = {'output_dim': self.output_dim,
+                  'init': self.init.__name__,
+                  'inner_init': self.inner_init.__name__,
+                  'activation': self.activation.__name__,
+                  'W_regularizer': self.W_regularizer.get_config() if self.W_regularizer else None,
+                  'U_regularizer': self.U_regularizer.get_config() if self.U_regularizer else None,
+                  'b_regularizer': self.b_regularizer.get_config() if self.b_regularizer else None,
+                  'dropout_W': self.dropout_W,
+                  'dropout_U': self.dropout_U}
         base_config = super(SimpleRNN, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
 
@@ -256,86 +417,204 @@ class GRU(Recurrent):
             Can be the name of an existing function (str),
             or a Theano function (see: [activations](../activations.md)).
         inner_activation: activation function for the inner cells.
+        W_regularizer: instance of [WeightRegularizer](../regularizers.md)
+            (eg. L1 or L2 regularization), applied to the input weights matrices.
+        U_regularizer: instance of [WeightRegularizer](../regularizers.md)
+            (eg. L1 or L2 regularization), applied to the recurrent weights matrices.
+        b_regularizer: instance of [WeightRegularizer](../regularizers.md),
+            applied to the bias.
+        dropout_W: float between 0 and 1. Fraction of the input units to drop for input gates.
+        dropout_U: float between 0 and 1. Fraction of the input units to drop for recurrent connections.
 
     # References
         - [On the Properties of Neural Machine Translation: Encoder–Decoder Approaches](http://www.aclweb.org/anthology/W14-4012)
         - [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](http://arxiv.org/pdf/1412.3555v1.pdf)
+        - [A Theoretically Grounded Application of Dropout in Recurrent Neural Networks](http://arxiv.org/abs/1512.05287)
     '''
     def __init__(self, output_dim,
                  init='glorot_uniform', inner_init='orthogonal',
-                 activation='sigmoid', inner_activation='hard_sigmoid',
-                 **kwargs):
+                 activation='tanh', inner_activation='hard_sigmoid',
+                 W_regularizer=None, U_regularizer=None, b_regularizer=None,
+                 dropout_W=0., dropout_U=0., **kwargs):
         self.output_dim = output_dim
         self.init = initializations.get(init)
         self.inner_init = initializations.get(inner_init)
         self.activation = activations.get(activation)
         self.inner_activation = activations.get(inner_activation)
+        self.W_regularizer = regularizers.get(W_regularizer)
+        self.U_regularizer = regularizers.get(U_regularizer)
+        self.b_regularizer = regularizers.get(b_regularizer)
+        self.dropout_W, self.dropout_U = dropout_W, dropout_U
+
+        if self.dropout_W or self.dropout_U:
+            self.uses_learning_phase = True
         super(GRU, self).__init__(**kwargs)
 
-    def build(self):
-        input_shape = self.input_shape
-        input_dim = input_shape[2]
-        self.input_dim = input_dim
-        self.input = K.placeholder(input_shape)
+    def build(self, input_shape):
+        self.input_spec = [InputSpec(shape=input_shape)]
+        self.input_dim = input_shape[2]
 
-        self.W_z = self.init((input_dim, self.output_dim))
-        self.U_z = self.inner_init((self.output_dim, self.output_dim))
-        self.b_z = K.zeros((self.output_dim,))
-
-        self.W_r = self.init((input_dim, self.output_dim))
-        self.U_r = self.inner_init((self.output_dim, self.output_dim))
-        self.b_r = K.zeros((self.output_dim,))
-
-        self.W_h = self.init((input_dim, self.output_dim))
-        self.U_h = self.inner_init((self.output_dim, self.output_dim))
-        self.b_h = K.zeros((self.output_dim,))
-
-        self.trainable_weights = [self.W_z, self.U_z, self.b_z,
-                                  self.W_r, self.U_r, self.b_r,
-                                  self.W_h, self.U_h, self.b_h]
         if self.stateful:
             self.reset_states()
         else:
             # initial states: all-zero tensor of shape (output_dim)
             self.states = [None]
 
+        if self.consume_less == 'gpu':
+
+            self.W = self.init((self.input_dim, 3 * self.output_dim),
+                               name='{}_W'.format(self.name))
+            self.U = self.inner_init((self.output_dim, 3 * self.output_dim),
+                                     name='{}_U'.format(self.name))
+
+            self.b = K.variable(np.hstack((np.zeros(self.output_dim),
+                                           np.zeros(self.output_dim),
+                                           np.zeros(self.output_dim))),
+                                name='{}_b'.format(self.name))
+
+            self.trainable_weights = [self.W, self.U, self.b]
+        else:
+
+            self.W_z = self.init((self.input_dim, self.output_dim),
+                                 name='{}_W_z'.format(self.name))
+            self.U_z = self.inner_init((self.output_dim, self.output_dim),
+                                       name='{}_U_z'.format(self.name))
+            self.b_z = K.zeros((self.output_dim,), name='{}_b_z'.format(self.name))
+
+            self.W_r = self.init((self.input_dim, self.output_dim),
+                                 name='{}_W_r'.format(self.name))
+            self.U_r = self.inner_init((self.output_dim, self.output_dim),
+                                       name='{}_U_r'.format(self.name))
+            self.b_r = K.zeros((self.output_dim,), name='{}_b_r'.format(self.name))
+
+            self.W_h = self.init((self.input_dim, self.output_dim),
+                                 name='{}_W_h'.format(self.name))
+            self.U_h = self.inner_init((self.output_dim, self.output_dim),
+                                       name='{}_U_h'.format(self.name))
+            self.b_h = K.zeros((self.output_dim,), name='{}_b_h'.format(self.name))
+
+            self.trainable_weights = [self.W_z, self.U_z, self.b_z,
+                                      self.W_r, self.U_r, self.b_r,
+                                      self.W_h, self.U_h, self.b_h]
+
+            self.W = K.concatenate([self.W_z, self.W_r, self.W_h])
+            self.U = K.concatenate([self.U_z, self.U_r, self.U_h])
+            self.b = K.concatenate([self.b_z, self.b_r, self.b_h])
+
+        self.regularizers = []
+        if self.W_regularizer:
+            self.W_regularizer.set_param(self.W)
+            self.regularizers.append(self.W_regularizer)
+        if self.U_regularizer:
+            self.U_regularizer.set_param(self.U)
+            self.regularizers.append(self.U_regularizer)
+        if self.b_regularizer:
+            self.b_regularizer.set_param(self.b)
+            self.regularizers.append(self.b_regularizer)
+
         if self.initial_weights is not None:
             self.set_weights(self.initial_weights)
             del self.initial_weights
 
     def reset_states(self):
         assert self.stateful, 'Layer must be stateful.'
-        input_shape = self.input_shape
+        input_shape = self.input_spec[0].shape
         if not input_shape[0]:
             raise Exception('If a RNN is stateful, a complete ' +
-                            'input_shape must be provided ' +
-                            '(including batch size).')
+                            'input_shape must be provided (including batch size).')
         if hasattr(self, 'states'):
             K.set_value(self.states[0],
                         np.zeros((input_shape[0], self.output_dim)))
         else:
             self.states = [K.zeros((input_shape[0], self.output_dim))]
 
+    def preprocess_input(self, x):
+        if self.consume_less == 'cpu':
+            input_shape = self.input_spec[0].shape
+            input_dim = input_shape[2]
+            timesteps = input_shape[1]
+
+            x_z = time_distributed_dense(x, self.W_z, self.b_z, self.dropout_W,
+                                         input_dim, self.output_dim, timesteps)
+            x_r = time_distributed_dense(x, self.W_r, self.b_r, self.dropout_W,
+                                         input_dim, self.output_dim, timesteps)
+            x_h = time_distributed_dense(x, self.W_h, self.b_h, self.dropout_W,
+                                         input_dim, self.output_dim, timesteps)
+            return K.concatenate([x_z, x_r, x_h], axis=2)
+        else:
+            return x
+
     def step(self, x, states):
-        assert len(states) == 1
-        x_z = K.dot(x, self.W_z) + self.b_z
-        x_r = K.dot(x, self.W_r) + self.b_r
-        x_h = K.dot(x, self.W_h) + self.b_h
+        h_tm1 = states[0]  # previous memory
+        B_U = states[1]  # dropout matrices for recurrent units
+        B_W = states[2]
 
-        h_tm1 = states[0]
-        z = self.inner_activation(x_z + K.dot(h_tm1, self.U_z))
-        r = self.inner_activation(x_r + K.dot(h_tm1, self.U_r))
+        if self.consume_less == 'gpu':
 
-        hh = self.activation(x_h + K.dot(r * h_tm1, self.U_h))
+            matrix_x = K.dot(x * B_W[0], self.W) + self.b
+            matrix_inner = K.dot(h_tm1 * B_U[0], self.U[:, :2 * self.output_dim])
+
+            x_z = matrix_x[:, :self.output_dim]
+            x_r = matrix_x[:, self.output_dim: 2 * self.output_dim]
+            inner_z = matrix_inner[:, :self.output_dim]
+            inner_r = matrix_inner[:, self.output_dim: 2 * self.output_dim]
+
+            z = self.inner_activation(x_z + inner_z)
+            r = self.inner_activation(x_r + inner_r)
+
+            x_h = matrix_x[:, 2 * self.output_dim:]
+            inner_h = K.dot(r * h_tm1 * B_U[0], self.U[:, 2 * self.output_dim:])
+            hh = self.activation(x_h + inner_h)
+        else:
+            if self.consume_less == 'cpu':
+                x_z = x[:, :self.output_dim]
+                x_r = x[:, self.output_dim: 2 * self.output_dim]
+                x_h = x[:, 2 * self.output_dim:]
+            elif self.consume_less == 'mem':
+                x_z = K.dot(x * B_W[0], self.W_z) + self.b_z
+                x_r = K.dot(x * B_W[1], self.W_r) + self.b_r
+                x_h = K.dot(x * B_W[2], self.W_h) + self.b_h
+            else:
+                raise Exception('Unknown `consume_less` mode.')
+            z = self.inner_activation(x_z + K.dot(h_tm1 * B_U[0], self.U_z))
+            r = self.inner_activation(x_r + K.dot(h_tm1 * B_U[1], self.U_r))
+
+            hh = self.activation(x_h + K.dot(r * h_tm1 * B_U[2], self.U_h))
         h = z * h_tm1 + (1 - z) * hh
         return h, [h]
 
+    def get_constants(self, x):
+        constants = []
+        if 0 < self.dropout_U < 1:
+            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
+            ones = K.concatenate([ones] * self.output_dim, 1)
+            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
+            constants.append(B_U)
+        else:
+            constants.append([K.cast_to_floatx(1.) for _ in range(3)])
+
+        if 0 < self.dropout_W < 1:
+            input_shape = self.input_spec[0].shape
+            input_dim = input_shape[-1]
+            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
+            ones = K.concatenate([ones] * input_dim, 1)
+            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
+            constants.append(B_W)
+        else:
+            constants.append([K.cast_to_floatx(1.) for _ in range(3)])
+        return constants
+
     def get_config(self):
-        config = {"output_dim": self.output_dim,
-                  "init": self.init.__name__,
-                  "inner_init": self.inner_init.__name__,
-                  "activation": self.activation.__name__,
-                  "inner_activation": self.inner_activation.__name__}
+        config = {'output_dim': self.output_dim,
+                  'init': self.init.__name__,
+                  'inner_init': self.inner_init.__name__,
+                  'activation': self.activation.__name__,
+                  'inner_activation': self.inner_activation.__name__,
+                  'W_regularizer': self.W_regularizer.get_config() if self.W_regularizer else None,
+                  'U_regularizer': self.U_regularizer.get_config() if self.U_regularizer else None,
+                  'b_regularizer': self.b_regularizer.get_config() if self.b_regularizer else None,
+                  'dropout_W': self.dropout_W,
+                  'dropout_U': self.dropout_U}
         base_config = super(GRU, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
 
@@ -359,56 +638,109 @@ class LSTM(Recurrent):
             Can be the name of an existing function (str),
             or a Theano function (see: [activations](../activations.md)).
         inner_activation: activation function for the inner cells.
+        W_regularizer: instance of [WeightRegularizer](../regularizers.md)
+            (eg. L1 or L2 regularization), applied to the input weights matrices.
+        U_regularizer: instance of [WeightRegularizer](../regularizers.md)
+            (eg. L1 or L2 regularization), applied to the recurrent weights matrices.
+        b_regularizer: instance of [WeightRegularizer](../regularizers.md),
+            applied to the bias.
+        dropout_W: float between 0 and 1. Fraction of the input units to drop for input gates.
+        dropout_U: float between 0 and 1. Fraction of the input units to drop for recurrent connections.
 
     # References
         - [Long short-term memory](http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf) (original 1997 paper)
         - [Learning to forget: Continual prediction with LSTM](http://www.mitpressjournals.org/doi/pdf/10.1162/089976600300015015)
         - [Supervised sequence labelling with recurrent neural networks](http://www.cs.toronto.edu/~graves/preprint.pdf)
+        - [A Theoretically Grounded Application of Dropout in Recurrent Neural Networks](http://arxiv.org/abs/1512.05287)
     '''
     def __init__(self, output_dim,
                  init='glorot_uniform', inner_init='orthogonal',
                  forget_bias_init='one', activation='tanh',
-                 inner_activation='hard_sigmoid', **kwargs):
+                 inner_activation='hard_sigmoid',
+                 W_regularizer=None, U_regularizer=None, b_regularizer=None,
+                 dropout_W=0., dropout_U=0., **kwargs):
         self.output_dim = output_dim
         self.init = initializations.get(init)
         self.inner_init = initializations.get(inner_init)
         self.forget_bias_init = initializations.get(forget_bias_init)
         self.activation = activations.get(activation)
         self.inner_activation = activations.get(inner_activation)
+        self.W_regularizer = regularizers.get(W_regularizer)
+        self.U_regularizer = regularizers.get(U_regularizer)
+        self.b_regularizer = regularizers.get(b_regularizer)
+        self.dropout_W, self.dropout_U = dropout_W, dropout_U
+
+        if self.dropout_W or self.dropout_U:
+            self.uses_learning_phase = True
         super(LSTM, self).__init__(**kwargs)
 
-    def build(self):
-        input_shape = self.input_shape
-        input_dim = input_shape[2]
-        self.input_dim = input_dim
-        self.input = K.placeholder(input_shape)
+    def build(self, input_shape):
+        self.input_spec = [InputSpec(shape=input_shape)]
+        self.input_dim = input_shape[2]
 
         if self.stateful:
             self.reset_states()
         else:
-            # initial states: 2 all-zero tensor of shape (output_dim)
+            # initial states: 2 all-zero tensors of shape (output_dim)
             self.states = [None, None]
 
-        self.W_i = self.init((input_dim, self.output_dim))
-        self.U_i = self.inner_init((self.output_dim, self.output_dim))
-        self.b_i = K.zeros((self.output_dim,))
+        if self.consume_less == 'gpu':
+            self.W = self.init((self.input_dim, 4 * self.output_dim),
+                               name='{}_W'.format(self.name))
+            self.U = self.inner_init((self.output_dim, 4 * self.output_dim),
+                                     name='{}_U'.format(self.name))
 
-        self.W_f = self.init((input_dim, self.output_dim))
-        self.U_f = self.inner_init((self.output_dim, self.output_dim))
-        self.b_f = self.forget_bias_init((self.output_dim,))
+            self.b = K.variable(np.hstack((np.zeros(self.output_dim),
+                                           K.get_value(self.forget_bias_init(self.output_dim)),
+                                           np.zeros(self.output_dim),
+                                           np.zeros(self.output_dim))),
+                                name='{}_b'.format(self.name))
+            self.trainable_weights = [self.W, self.U, self.b]
+        else:
+            self.W_i = self.init((self.input_dim, self.output_dim),
+                                 name='{}_W_i'.format(self.name))
+            self.U_i = self.inner_init((self.output_dim, self.output_dim),
+                                       name='{}_U_i'.format(self.name))
+            self.b_i = K.zeros((self.output_dim,), name='{}_b_i'.format(self.name))
 
-        self.W_c = self.init((input_dim, self.output_dim))
-        self.U_c = self.inner_init((self.output_dim, self.output_dim))
-        self.b_c = K.zeros((self.output_dim,))
+            self.W_f = self.init((self.input_dim, self.output_dim),
+                                 name='{}_W_f'.format(self.name))
+            self.U_f = self.inner_init((self.output_dim, self.output_dim),
+                                       name='{}_U_f'.format(self.name))
+            self.b_f = self.forget_bias_init((self.output_dim,),
+                                             name='{}_b_f'.format(self.name))
 
-        self.W_o = self.init((input_dim, self.output_dim))
-        self.U_o = self.inner_init((self.output_dim, self.output_dim))
-        self.b_o = K.zeros((self.output_dim,))
+            self.W_c = self.init((self.input_dim, self.output_dim),
+                                 name='{}_W_c'.format(self.name))
+            self.U_c = self.inner_init((self.output_dim, self.output_dim),
+                                       name='{}_U_c'.format(self.name))
+            self.b_c = K.zeros((self.output_dim,), name='{}_b_c'.format(self.name))
 
-        self.trainable_weights = [self.W_i, self.U_i, self.b_i,
-                                  self.W_c, self.U_c, self.b_c,
-                                  self.W_f, self.U_f, self.b_f,
-                                  self.W_o, self.U_o, self.b_o]
+            self.W_o = self.init((self.input_dim, self.output_dim),
+                                 name='{}_W_o'.format(self.name))
+            self.U_o = self.inner_init((self.output_dim, self.output_dim),
+                                       name='{}_U_o'.format(self.name))
+            self.b_o = K.zeros((self.output_dim,), name='{}_b_o'.format(self.name))
+
+            self.trainable_weights = [self.W_i, self.U_i, self.b_i,
+                                      self.W_c, self.U_c, self.b_c,
+                                      self.W_f, self.U_f, self.b_f,
+                                      self.W_o, self.U_o, self.b_o]
+
+            self.W = K.concatenate([self.W_i, self.W_f, self.W_c, self.W_o])
+            self.U = K.concatenate([self.U_i, self.U_f, self.U_c, self.U_o])
+            self.b = K.concatenate([self.b_i, self.b_f, self.b_c, self.b_o])
+
+        self.regularizers = []
+        if self.W_regularizer:
+            self.W_regularizer.set_param(self.W)
+            self.regularizers.append(self.W_regularizer)
+        if self.U_regularizer:
+            self.U_regularizer.set_param(self.U)
+            self.regularizers.append(self.U_regularizer)
+        if self.b_regularizer:
+            self.b_regularizer.set_param(self.b)
+            self.regularizers.append(self.b_regularizer)
 
         if self.initial_weights is not None:
             self.set_weights(self.initial_weights)
@@ -416,11 +748,10 @@ class LSTM(Recurrent):
 
     def reset_states(self):
         assert self.stateful, 'Layer must be stateful.'
-        input_shape = self.input_shape
+        input_shape = self.input_spec[0].shape
         if not input_shape[0]:
             raise Exception('If a RNN is stateful, a complete ' +
-                            'input_shape must be provided ' +
-                            '(including batch size).')
+                            'input_shape must be provided (including batch size).')
         if hasattr(self, 'states'):
             K.set_value(self.states[0],
                         np.zeros((input_shape[0], self.output_dim)))
@@ -430,29 +761,100 @@ class LSTM(Recurrent):
             self.states = [K.zeros((input_shape[0], self.output_dim)),
                            K.zeros((input_shape[0], self.output_dim))]
 
+    def preprocess_input(self, x):
+        if self.consume_less == 'cpu':
+            if 0 < self.dropout_W < 1:
+                dropout = self.dropout_W
+            else:
+                dropout = 0
+            input_shape = self.input_spec[0].shape
+            input_dim = input_shape[2]
+            timesteps = input_shape[1]
+
+            x_i = time_distributed_dense(x, self.W_i, self.b_i, dropout,
+                                         input_dim, self.output_dim, timesteps)
+            x_f = time_distributed_dense(x, self.W_f, self.b_f, dropout,
+                                         input_dim, self.output_dim, timesteps)
+            x_c = time_distributed_dense(x, self.W_c, self.b_c, dropout,
+                                         input_dim, self.output_dim, timesteps)
+            x_o = time_distributed_dense(x, self.W_o, self.b_o, dropout,
+                                         input_dim, self.output_dim, timesteps)
+            return K.concatenate([x_i, x_f, x_c, x_o], axis=2)
+        else:
+            return x
+
     def step(self, x, states):
-        assert len(states) == 2
         h_tm1 = states[0]
         c_tm1 = states[1]
+        B_U = states[2]
+        B_W = states[3]
 
-        x_i = K.dot(x, self.W_i) + self.b_i
-        x_f = K.dot(x, self.W_f) + self.b_f
-        x_c = K.dot(x, self.W_c) + self.b_c
-        x_o = K.dot(x, self.W_o) + self.b_o
+        if self.consume_less == 'gpu':
+            z = K.dot(x * B_W[0], self.W) + K.dot(h_tm1 * B_U[0], self.U) + self.b
+
+            z0 = z[:, :self.output_dim]
+            z1 = z[:, self.output_dim: 2 * self.output_dim]
+            z2 = z[:, 2 * self.output_dim: 3 * self.output_dim]
+            z3 = z[:, 3 * self.output_dim:]
+
+            i = self.inner_activation(z0)
+            f = self.inner_activation(z1)
+            c = f * c_tm1 + i * self.activation(z2)
+            o = self.inner_activation(z3)
+        else:
+            if self.consume_less == 'cpu':
+                x_i = x[:, :self.output_dim]
+                x_f = x[:, self.output_dim: 2 * self.output_dim]
+                x_c = x[:, 2 * self.output_dim: 3 * self.output_dim]
+                x_o = x[:, 3 * self.output_dim:]
+            elif self.consume_less == 'mem':
+                x_i = K.dot(x * B_W[0], self.W_i) + self.b_i
+                x_f = K.dot(x * B_W[1], self.W_f) + self.b_f
+                x_c = K.dot(x * B_W[2], self.W_c) + self.b_c
+                x_o = K.dot(x * B_W[3], self.W_o) + self.b_o
+            else:
+                raise Exception('Unknown `consume_less` mode.')
+
+            i = self.inner_activation(x_i + K.dot(h_tm1 * B_U[0], self.U_i))
+            f = self.inner_activation(x_f + K.dot(h_tm1 * B_U[1], self.U_f))
+            c = f * c_tm1 + i * self.activation(x_c + K.dot(h_tm1 * B_U[2], self.U_c))
+            o = self.inner_activation(x_o + K.dot(h_tm1 * B_U[3], self.U_o))
 
-        i = self.inner_activation(x_i + K.dot(h_tm1, self.U_i))
-        f = self.inner_activation(x_f + K.dot(h_tm1, self.U_f))
-        c = f * c_tm1 + i * self.activation(x_c + K.dot(h_tm1, self.U_c))
-        o = self.inner_activation(x_o + K.dot(h_tm1, self.U_o))
         h = o * self.activation(c)
         return h, [h, c]
 
+    def get_constants(self, x):
+        constants = []
+        if 0 < self.dropout_U < 1:
+            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
+            ones = K.concatenate([ones] * self.output_dim, 1)
+            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)]
+            constants.append(B_U)
+        else:
+            constants.append([K.cast_to_floatx(1.) for _ in range(4)])
+
+        if 0 < self.dropout_W < 1:
+            input_shape = self.input_spec[0].shape
+            input_dim = input_shape[-1]
+            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
+            ones = K.concatenate([ones] * input_dim, 1)
+            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)]
+            constants.append(B_W)
+        else:
+            constants.append([K.cast_to_floatx(1.) for _ in range(4)])
+        return constants
+
     def get_config(self):
-        config = {"output_dim": self.output_dim,
-                  "init": self.init.__name__,
-                  "inner_init": self.inner_init.__name__,
-                  "forget_bias_init": self.forget_bias_init.__name__,
-                  "activation": self.activation.__name__,
-                  "inner_activation": self.inner_activation.__name__}
+        config = {'output_dim': self.output_dim,
+                  'init': self.init.__name__,
+                  'inner_init': self.inner_init.__name__,
+                  'forget_bias_init': self.forget_bias_init.__name__,
+                  'activation': self.activation.__name__,
+                  'inner_activation': self.inner_activation.__name__,
+                  'W_regularizer': self.W_regularizer.get_config() if self.W_regularizer else None,
+                  'U_regularizer': self.U_regularizer.get_config() if self.U_regularizer else None,
+                  'b_regularizer': self.b_regularizer.get_config() if self.b_regularizer else None,
+                  'dropout_W': self.dropout_W,
+                  'dropout_U': self.dropout_U}
         base_config = super(LSTM, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))

keras/layers/wrappers.py

@@ -0,0 +1,135 @@
+from ..engine import Layer, InputSpec
+from .. import backend as K
+
+
+class Wrapper(Layer):
+
+    def __init__(self, layer, **kwargs):
+        self.layer = layer
+        self.uses_learning_phase = layer.uses_learning_phase
+        super(Wrapper, self).__init__(**kwargs)
+
+    def build(self, input_shape=None):
+        '''Assumes that self.layer is already set.
+        Should be called at the end of .build() in the
+        children classes.
+        '''
+        self.trainable_weights = getattr(self.layer, 'trainable_weights', [])
+        self.non_trainable_weights = getattr(self.layer, 'non_trainable_weights', [])
+        self.updates = getattr(self.layer, 'updates', [])
+        self.regularizers = getattr(self.layer, 'regularizers', [])
+        self.constraints = getattr(self.layer, 'constraints', {})
+
+    def get_weights(self):
+        weights = self.layer.get_weights()
+        return weights
+
+    def set_weights(self, weights):
+        self.layer.set_weights(weights)
+
+    def get_config(self):
+        config = {'layer': {'class_name': self.layer.__class__.__name__,
+                            'config': self.layer.get_config()}}
+        base_config = super(Wrapper, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))
+
+    @classmethod
+    def from_config(cls, config):
+        from keras.utils.layer_utils import layer_from_config
+        layer = layer_from_config(config.pop('layer'))
+        return cls(layer, **config)
+
+
+class TimeDistributed(Wrapper):
+    """This wrapper allows to apply a layer to every
+    temporal slice of an input.
+
+    The input should be at least 3D,
+    and the dimension of index one will be considered to be
+    the temporal dimension.
+
+    Consider a batch of 32 samples, where each sample is a sequence of 10
+    vectors of 16 dimensions. The batch input shape of the layer is then `(32, 10, 16)`
+    (and the `input_shape`, not including the samples dimension, is `(10, 16)`).
+
+    You can then use `TimeDistributed` to apply a `Dense` layer to each of the 10 timesteps, independently:
+    ```python
+        # as the first layer in a model
+        model = Sequential()
+        model.add(TimeDistributed(Dense(8), input_shape=(10, 16)))
+        # now model.output_shape == (None, 10, 8)
+
+        # subsequent layers: no need for input_shape
+        model.add(TimeDistributed(Dense(32)))
+        # now model.output_shape == (None, 10, 32)
+    ```
+
+    The output will then have shape `(32, 10, 8)`.
+
+    Note this is strictly equivalent to using `layers.core.TimeDistributedDense`.
+    However what is different about `TimeDistributed`
+    is that it can be used with arbitrary layers, not just `Dense`,
+    for instance with a `Convolution2D` layer:
+
+    ```python
+        model = Sequential()
+        model.add(TimeDistributed(Convolution2D(64, 3, 3), input_shape=(10, 3, 299, 299)))
+    ```
+
+    # Arguments
+        layer: a layer instance.
+    """
+    def __init__(self, layer, **kwargs):
+        self.supports_masking = True
+        super(TimeDistributed, self).__init__(layer, **kwargs)
+
+    def build(self, input_shape):
+        assert len(input_shape) >= 3
+        self.input_spec = [InputSpec(shape=input_shape)]
+        if K._BACKEND == 'tensorflow':
+            if not input_shape[1]:
+                raise Exception('When using TensorFlow, you should define '
+                                'explicitly the number of timesteps of '
+                                'your sequences.\n'
+                                'If your first layer is an Embedding, '
+                                'make sure to pass it an "input_length" '
+                                'argument. Otherwise, make sure '
+                                'the first layer has '
+                                'an "input_shape" or "batch_input_shape" '
+                                'argument, including the time axis.')
+        child_input_shape = (input_shape[0],) + input_shape[2:]
+        if not self.layer.built:
+            self.layer.build(child_input_shape)
+            self.layer.built = True
+        super(TimeDistributed, self).build()
+
+    def get_output_shape_for(self, input_shape):
+        child_input_shape = (input_shape[0],) + input_shape[2:]
+        child_output_shape = self.layer.get_output_shape_for(child_input_shape)
+        timesteps = input_shape[1]
+        return (child_output_shape[0], timesteps) + child_output_shape[1:]
+
+    def call(self, X, mask=None):
+        input_shape = self.input_spec[0].shape
+        if input_shape[0]:
+            # batch size matters, use rnn-based implementation
+            def step(x, states):
+                output = self.layer.call(x)
+                return output, []
+
+            last_output, outputs, states = K.rnn(step, X,
+                                                 initial_states=[])
+            y = outputs
+        else:
+            # no batch size specified, therefore the layer will be able
+            # to process batches of any size
+            # we can go with reshape-based implementation for performance
+            input_length = input_shape[1]
+            if not input_length:
+                input_length = K.shape(X)[1]
+            X = K.reshape(X, (-1, ) + input_shape[2:])  # (nb_samples * timesteps, ...)
+            y = self.layer.call(X)  # (nb_samples * timesteps, ...)
+            # (nb_samples, timesteps, ...)
+            output_shape = self.get_output_shape_for(input_shape)
+            y = K.reshape(y, (-1, input_length) + output_shape[2:])
+        return y

keras/legacy/models.py

@@ -0,0 +1,775 @@
+from collections import OrderedDict
+import warnings
+import copy
+
+from .. import backend as K
+from ..layers import InputLayer, Layer, Merge
+from ..engine.training import Model
+
+
+class Graph(Model):
+    '''Arbitrary connection graph.
+
+    THIS IS A LEGACY MODEL AND SHOULD NOT BE USED
+    except for backwards compatibility support.
+
+    For multi-inputs/multi-outputs models, or
+    models using shared layers, use the functional API instead.
+    '''
+
+    def __init__(self, name=None):
+        # model attributes
+        self.inbound_nodes = []
+        self.outbound_nodes = []
+        self.built = False
+        self.supports_masking = False
+
+        # legacy attributes (we prefix them with _graph_)
+        self._graph_namespace = set()  # strings
+        self._graph_nodes = OrderedDict()  # layer-like
+        self._graph_inputs = OrderedDict()  # layer-like
+        self._graph_outputs = OrderedDict()  # layer-like
+        self._graph_input_config = []  # dicts
+        self._graph_output_config = []  # dicts
+        self._graph_node_config = []  # dicts
+        self._graph_shared_nodes_names = []
+
+        if not name:
+            prefix = 'graph_'
+            name = prefix + str(K.get_uid(prefix))
+        self.name = name
+
+    def __call__(self, x, mask=None):
+        self.build()
+        return super(Graph, self).__call__(x, mask)
+
+    def build(self, input_shape=None):
+        # this will crash if the input/output layers have multiple nodes
+        # no plans to support that case since Graph is deprecated
+        input_tensors = [layer.output for layer in self._graph_inputs.values()]
+        output_tensors = [layer.output for layer in self._graph_outputs.values()]
+        # actually create the model
+        super(Graph, self).__init__(input_tensors,
+                                    output_tensors,
+                                    name=self.name)
+        self.built = True
+
+    def compile(self, optimizer, loss,
+                metrics=[],
+                sample_weight_modes=None,
+                loss_weights=None,
+                **kwargs):
+        '''Configures the learning process.
+
+        # Arguments
+            optimizer: str (name of optimizer) or optimizer object.
+                See [optimizers](optimizers.md).
+            loss: dictionary mapping the name(s) of the output(s) to
+                a loss function (string name of objective function or
+                objective function. See [objectives](objectives.md)).
+            metrics: list of str (name of metrics) or
+                list of metrics functions. See [metrics](metrics.md).
+            sample_weight_modes: optional dictionary mapping certain
+                output names to a sample weight mode ("temporal" and None
+                are the only supported modes). If you need to do
+                timestep-wise loss weighting on one of your graph outputs,
+                you will need to set the sample weight mode for this output
+                to "temporal".
+            loss_weights: dictionary you can pass to specify a weight
+                coefficient for each loss function (in a multi-output model).
+                If no loss weight is specified for an output,
+                the weight for this output's loss will be considered to be 1.
+            kwargs: for Theano backend, these are passed into K.function.
+                Ignored for Tensorflow backend.
+        '''
+        # create the underlying Model
+        if not self.built:
+            self.build()
+        super(Graph, self).compile(optimizer, loss,
+                                   metrics=metrics,
+                                   sample_weight_mode=sample_weight_modes,
+                                   loss_weights=loss_weights,
+                                   **kwargs)
+
+    def add_input(self, name, input_shape=None,
+                  batch_input_shape=None, dtype='float'):
+        '''Adds an input to the graph.
+
+        # Arguments:
+            name: string. The name of the new input.
+                Must be unique in the graph.
+            input_shape: a tuple of integers,
+                the expected shape of the input samples.
+                Does not include the batch size.
+            batch_input_shape: a tuple of integers,
+                the expected shape of the whole input batch,
+                including the batch size.
+            dtype: 'float', or 'int'.
+        '''
+        if name in self._graph_namespace:
+            raise Exception('Duplicate node identifier: ' + name)
+        self._graph_namespace.add(name)
+        self.built = False
+
+        if dtype[:3] == 'int':
+            dtype = 'int32'
+        elif dtype[:5] == 'float':
+            dtype = K.floatx()
+        else:
+            raise Exception('Uknown dtype (should be "int" or "float"): ' +
+                            str(dtype))
+
+        # create input layer
+        input_layer = InputLayer(input_shape=input_shape,
+                                 batch_input_shape=batch_input_shape,
+                                 name=name, input_dtype=dtype)
+        self._graph_inputs[name] = input_layer
+
+        # append input config to self._graph_input_config
+        config = {'name': name, 'dtype': dtype}
+        if batch_input_shape:
+            config['batch_input_shape'] = batch_input_shape
+        else:
+            config['input_shape'] = input_shape
+        self._graph_input_config.append(config)
+
+    def add_node(self, layer, name, input=None, inputs=[],
+                 merge_mode='concat', concat_axis=-1, dot_axes=-1,
+                 create_output=False):
+        '''Adds a node in the graph. It can be connected to multiple
+        inputs, which will first be merged into one tensor
+        according to the mode specified.
+
+        # Arguments
+            layer: the layer at the node.
+            name: name for the node.
+            input: when connecting the layer to a single input,
+                this is the name of the incoming node.
+            inputs: when connecting the layer to multiple inputs,
+                this is a list of names of incoming nodes.
+            merge_mode: one of {concat, sum, dot, ave, mul}
+            concat_axis: when `merge_mode=='concat'`, this is the
+                input concatenation axis.
+            dot_axes: when `merge_mode='dot'`,
+                this is the contraction axes specification;
+                see the `Merge` layer for details.
+            create_output: boolean. Set this to `True` if you want the output
+                of your node to be an output of the graph.
+        '''
+        if name in self._graph_namespace:
+            raise Exception('Duplicate node identifier: ' + name)
+        self._graph_namespace.add(name)
+        layer.name = name
+        self.built = False
+
+        if input:
+            if input not in self._graph_namespace:
+                raise Exception('Unknown node/input identifier: ' + input)
+            if input in self._graph_nodes:
+                layer.add_inbound_node(self._graph_nodes[input])
+            elif input in self._graph_inputs:
+                layer.add_inbound_node(self._graph_inputs[input])
+        if inputs:
+            to_merge = []
+            for n in inputs:
+                if n in self._graph_nodes:
+                    to_merge.append(self._graph_nodes[n])
+                elif n in self._graph_inputs:
+                    to_merge.append(self._graph_inputs[n])
+                else:
+                    raise Exception('Unknown identifier: ' + n)
+            merge = Merge(to_merge, mode=merge_mode,
+                          concat_axis=concat_axis, dot_axes=dot_axes,
+                          name='merge_inputs_for_' + name)
+            layer.add_inbound_node(merge)
+        self._graph_nodes[name] = layer
+        self._graph_node_config.append({'name': name,
+                                        'input': input,
+                                        'inputs': inputs,
+                                        'merge_mode': merge_mode,
+                                        'concat_axis': concat_axis,
+                                        'dot_axes': dot_axes,
+                                        'create_output': create_output})
+        if create_output:
+            self.add_output(name, input=name)
+
+    def add_shared_node(self, layer, name, inputs=[], merge_mode=None,
+                        concat_axis=-1, dot_axes=-1, outputs=[],
+                        create_output=False):
+        '''Used to share a same layer across multiple nodes.
+
+        Supposed, for instance, that you want to apply one same `Dense` layer
+        after two different nodes ('node_a' and 'node_b').
+        You can then add the dense layer as a shared node by calling:
+
+        ```python
+        model.add_shared_node(my_dense, name='shared_dense', inputs=['node_a', 'node_b'], ...)
+        ```
+
+        If you want access to the output of dense(node_a) and dense(node_b) separately,
+        you can add these outputs to the Graph by passing an `outputs` argument:
+
+        ```python
+        model.add_shared_node(my_dense, name='shared_dense', inputs=['node_a', 'node_b'],
+                              outputs=['dense_output_a', 'dense_outputs_b'])
+        ```
+
+        Otherwise you can merge these different outputs via `merge_mode`.
+        In that case you can access the merged output
+        under the identifier `name`.
+
+        # Arguments
+            layer: The layer to be shared across multiple inputs
+            name: Name of the shared node
+            inputs: List of names of input nodes
+            merge_mode: Same meaning as `merge_mode` argument of `add_node()`
+            concat_axis: Same meaning as `concat_axis` argument of `add_node()`
+            dot_axes: Same meaning as `dot_axes` argument of `add_node()`
+            outputs: Used when `merge_mode=None`. Names for the output nodes.
+            create_output: Same meaning as `create_output` argument of `add_node()`.
+        '''
+        if name in self._graph_namespace:
+            raise Exception('Duplicate node identifier: ' + name)
+        self._graph_namespace.add(name)
+        self.built = False
+
+        for o in outputs:
+            if o in self._graph_namespace:
+                raise Exception('Duplicate node identifier: ' + o)
+        if merge_mode:
+            if merge_mode not in {'sum', 'ave', 'mul', 'dot', 'cos', 'concat'}:
+                raise Exception('Invalid merge mode:', merge_mode)
+        input_layers = []
+        for i in range(len(inputs)):
+            input = inputs[i]
+            if input in self._graph_nodes:
+                n = self._graph_nodes[input]
+                input_layers.append(n)
+            elif input in self._graph_inputs:
+                n = self._graph_inputs[input]
+                input_layers.append(n)
+            else:
+                raise Exception('Unknown identifier: ' + input)
+
+        created_node_indices = []
+        for input_layer in input_layers:
+            created_node_indices.append(len(layer.inbound_nodes))
+            layer.add_inbound_node(input_layer)
+
+        if merge_mode:
+            layer.name = 'input_for_' + name
+            # collect all output nodes of layer and merge them into a single output
+            merge = Merge([layer for _ in range(len(inputs))],
+                          mode=merge_mode,
+                          concat_axis=concat_axis, dot_axes=dot_axes,
+                          node_indices=created_node_indices,
+                          name=name)
+            self._graph_nodes[name] = merge
+            if create_output:
+                self.add_output(name, input=name)
+        else:
+            layer.name = name
+            # create one new layer per output node of layer,
+            # and add them to the Graph with their own identifiers
+            if len(outputs) != len(inputs):
+                raise Exception('When using merge_mode=None, '
+                                'you should provide a list of '
+                                'output names (`output` argument) '
+                                'the same size as `input`.')
+            for i in range(len(outputs)):
+                output_layer_name = outputs[i]
+                output_layer = Layer(name=output_layer_name)
+                output_layer.add_inbound_node(layer, created_node_indices[i])
+                self._graph_namespace.add(output_layer_name)
+                self._graph_nodes[output_layer_name] = output_layer
+                if create_output:
+                    self.add_output(output_layer_name, input=output_layer_name)
+
+        self._graph_node_config.append({'name': name,
+                                        'layer': {
+                                            'config': layer.get_config(),
+                                            'class_name': layer.__class__.__name__,
+                                        },
+                                        'inputs': inputs,
+                                        'merge_mode': merge_mode,
+                                        'concat_axis': concat_axis,
+                                        'dot_axes': dot_axes,
+                                        'outputs': outputs,
+                                        'create_output': create_output if merge_mode else False})
+        self._graph_shared_nodes_names.append(name)
+
+    def add_output(self, name, input=None, inputs=[],
+                   merge_mode='concat', concat_axis=-1, dot_axes=-1):
+        '''Adds an output to the graph.
+
+        This output can merge several node outputs into a single output.
+
+        # Arguments
+            name: name of the output.
+            input: when connecting the layer to a single input,
+                this is the name of the incoming node.
+            inputs: when connecting the layer to multiple inputs,
+                this is a list of names of incoming nodes.
+            merge_mode: one of {concat, sum, dot, ave, mul}
+            concat_axis: when `merge_mode=='concat'`, this is the
+                input concatenation axis.
+            dot_axes: when `merge_mode='dot'`,
+                this is the contraction axes specification;
+                see the `Merge layer for details.
+        '''
+        if name not in self._graph_namespace:
+            self._graph_namespace.add(name)
+        if name in self._graph_outputs:
+            raise Exception('Duplicate output identifier:', name)
+        self.built = False
+
+        if input:
+            if input in self._graph_nodes:
+                layer = self._graph_nodes[input]
+            elif input in self._graph_inputs:
+                layer = self._graph_inputs[input]
+            else:
+                raise Exception('Unknown node/input identifier: ' + input)
+            if layer.name == name:
+                self._graph_outputs[name] = layer
+            else:
+                layer.name = name
+                self._graph_outputs[name] = layer
+        if inputs:
+            to_merge = []
+            for n in inputs:
+                if n not in self._graph_nodes:
+                    raise Exception('Unknown identifier: ' + n)
+                to_merge.append(self._graph_nodes[n])
+            merge = Merge(to_merge, mode=merge_mode,
+                          concat_axis=concat_axis, dot_axes=dot_axes,
+                          name=name)
+            self._graph_outputs[name] = merge
+
+        self._graph_output_config.append({'name': name,
+                                          'input': input,
+                                          'inputs': inputs,
+                                          'merge_mode': merge_mode,
+                                          'concat_axis': concat_axis,
+                                          'dot_axes': dot_axes})
+
+    def _get_x(self, data):
+        x = []
+        for key in self._graph_inputs.keys():
+            if key not in data:
+                raise Exception('Expected to be provided an array '
+                                '(in dict argument `data`) for input "' +
+                                key + '".')
+            x.append(data[key])
+        return x
+
+    def _get_y(self, data):
+        y = []
+        for key in self._graph_outputs.keys():
+            if key not in data:
+                raise Exception('Expected to be provided an array '
+                                '(in dict argument `data`) for output "' +
+                                key + '".')
+            y.append(data[key])
+        return y
+
+    def fit(self, data, batch_size=32, nb_epoch=10, verbose=1, callbacks=[],
+            validation_split=0., validation_data=None, shuffle=True,
+            class_weight=None, sample_weight=None, **kwargs):
+        '''Trains the model for a fixed number of epochs.
+
+        Returns a history object. Its `history` attribute is a record of
+        training loss values at successive epochs,
+        as well as validation loss values (if applicable).
+
+        # Arguments
+            data: dictionary mapping input names and outputs names to
+                appropriate numpy arrays. All arrays should contain
+                the same number of samples.
+            batch_size: int. Number of samples per gradient update.
+            nb_epoch: int.
+            verbose: 0 for no logging to stdout,
+                1 for progress bar logging, 2 for one log line per epoch.
+            callbacks: `keras.callbacks.Callback` list. List of callbacks
+                to apply during training. See [callbacks](callbacks.md).
+            validation_split: float (0. < x < 1). Fraction of the data to
+                use as held-out validation data.
+            validation_data: dictionary mapping input names and outputs names
+                to appropriate numpy arrays to be used as
+                held-out validation data.
+                All arrays should contain the same number of samples.
+                Will override validation_split.
+            shuffle: boolean. Whether to shuffle the samples at each epoch.
+            class_weight: dictionary mapping output names to
+                class weight dictionaries.
+            sample_weight: dictionary mapping output names to
+                numpy arrays of sample weights.
+        '''
+        if 'show_accuracy' in kwargs:
+            kwargs.pop('show_accuracy')
+            warnings.warn('The "show_accuracy" argument is deprecated, '
+                          'instead you should pass the "accuracy" metric to '
+                          'the model at compile time:\n'
+                          '`model.compile(optimizer, loss, '
+                          'metrics=["accuracy"])`')
+        if kwargs:
+            raise Exception('Received unknown keyword arguments: ' +
+                            str(kwargs))
+        x = self._get_x(data)
+        y = self._get_y(data)
+
+        if type(validation_data) is tuple:
+            raise Exception('Cannot used sample_weight with '
+                            'validation data with legacy Graph model. '
+                            'validation_data should be a dictionary.')
+        if validation_data:
+            val_x = self._get_x(validation_data)
+            val_y = self._get_y(validation_data)
+            validation_data = (val_x, val_y)
+        return super(Graph, self).fit(x, y,
+                                      batch_size=batch_size,
+                                      nb_epoch=nb_epoch,
+                                      verbose=verbose,
+                                      callbacks=callbacks,
+                                      validation_split=validation_split,
+                                      validation_data=validation_data,
+                                      shuffle=shuffle,
+                                      class_weight=class_weight,
+                                      sample_weight=sample_weight)
+
+    def evaluate(self, data, batch_size=128,
+                 verbose=0, sample_weight={}, **kwargs):
+        '''Computes the loss on some input data, batch by batch.
+
+        Returns the scalar test loss over the data,
+        or a list of metrics values (starting with the test loss)
+        if applicable.
+
+        Arguments: see `fit` method.
+        '''
+        if 'show_accuracy' in kwargs:
+            kwargs.pop('show_accuracy')
+            warnings.warn('The "show_accuracy" argument is deprecated, '
+                          'instead you should pass the "accuracy" metric to '
+                          'the model at compile time:\n'
+                          '`model.compile(optimizer, loss, '
+                          'metrics=["accuracy"])`')
+        if kwargs:
+            raise Exception('Received unknown keyword arguments: ' +
+                            str(kwargs))
+        x = self._get_x(data)
+        y = self._get_y(data)
+        return super(Graph, self).evaluate(x, y,
+                                           batch_size=batch_size,
+                                           verbose=verbose,
+                                           sample_weight=sample_weight)
+
+    def predict(self, data, batch_size=128, verbose=0):
+        '''Generates output predictions for the input samples
+        batch by batch.
+
+        Arguments: see `fit` method.
+        '''
+        x = self._get_x(data)
+        output_list = super(Graph, self).predict(x, batch_size=batch_size,
+                                                 verbose=verbose)
+        if not isinstance(output_list, list):
+            output_list = [output_list]
+        return dict(zip(self._graph_outputs, output_list))
+
+    def train_on_batch(self, data,
+                       class_weight={},
+                       sample_weight={}, **kwargs):
+        '''Single gradient update on a batch of samples.
+
+        Returns the scalar train loss over the data,
+        or a list of metrics values (starting with the test loss)
+        if applicable.
+
+        Arguments: see `fit` method.
+        '''
+        if 'accuracy' in kwargs:
+            kwargs.pop('accuracy')
+            warnings.warn('The "accuracy" argument is deprecated, '
+                          'instead you should pass the "accuracy" metric to '
+                          'the model at compile time:\n'
+                          '`model.compile(optimizer, loss, '
+                          'metrics=["accuracy"])`')
+        if kwargs:
+            raise Exception('Received unknown keyword arguments: ' +
+                            str(kwargs))
+        x = self._get_x(data)
+        y = self._get_y(data)
+        return super(Graph, self).train_on_batch(x, y,
+                                                 sample_weight=sample_weight,
+                                                 class_weight=class_weight)
+
+    def test_on_batch(self, data, sample_weight={}, **kwargs):
+        '''Test the network on a single batch of samples.
+
+        Returns the scalar test loss over the data,
+        or a list of metrics values (starting with the test loss)
+        if applicable.
+
+        Arguments: see `fit` method.
+        '''
+        if 'accuracy' in kwargs:
+            kwargs.pop('accuracy')
+            warnings.warn('The "accuracy" argument is deprecated, '
+                          'instead you should pass the "accuracy" metric to '
+                          'the model at compile time:\n'
+                          '`model.compile(optimizer, loss, '
+                          'metrics=["accuracy"])`')
+        if kwargs:
+            raise Exception('Received unknown keyword arguments: ' +
+                            str(kwargs))
+        x = self._get_x(data)
+        y = self._get_y(data)
+        return super(Graph, self).test_on_batch(x, y,
+                                                sample_weight=sample_weight)
+
+    def predict_on_batch(self, data):
+        output_list = super(Graph, self).predict_on_batch(data)
+        if not isinstance(output_list, list):
+            output_list = [output_list]
+        return dict(zip(self._graph_outputs, output_list))
+
+    def fit_generator(self, generator, samples_per_epoch, nb_epoch,
+                      verbose=1, callbacks=[],
+                      validation_data=None, nb_val_samples=None,
+                      class_weight={},
+                      max_q_size=10, **kwargs):
+        '''Fits a model on data generated batch-by-batch by a Python generator.
+        The generator is run in parallel to the model, for efficiency.
+        For instance, this allows you to do real-time data augmentation
+        on images on CPU in parallel to training your model on GPU.
+
+        # Arguments
+            generator: a generator.
+                The output of the generator must be either a tuple
+                of dictionaries `(input_data, sample_weight)`
+                or a dictionary `input_data`
+                (mapping names of inputs and outputs to Numpy arrays).
+                All arrays should contain the same number of samples.
+                The generator is expected to loop over its data
+                indefinitely. An epoch finishes when `samples_per_epoch`
+                samples have been seen by the model.
+            samples_per_epoch: integer, number of samples to process before
+                going to the next epoch.
+            nb_epoch: integer, total number of iterations on the data.
+            verbose: verbosity mode, 0, 1, or 2.
+            callbacks: list of callbacks to be called during training.
+            validation_data: dictionary mapping input names and outputs names
+                to appropriate numpy arrays to be used as
+                held-out validation data, or a generator yielding such
+                dictionaries. All arrays should contain the same number
+                of samples. If a generator, will be called until more than
+                `nb_val_samples` examples have been generated at the
+                end of every epoch. These examples will then be used
+                as the validation data.
+            nb_val_samples: number of samples to use from validation
+                generator at the end of every epoch.
+            class_weight: dictionary mapping class indices to a weight
+                for the class.
+
+        # Returns
+            A `History` object.
+
+        # Examples
+
+        ```python
+            def generate_arrays_from_file(path):
+                while 1:
+                    f = open(path)
+                    for line in f:
+                        # create numpy arrays of input data
+                        # and labels, from each line in the file
+                        x1, x2, y = process_line(line)
+                        yield ({'input_1': x1, 'input_2': x2, 'output': y})
+                    f.close()
+
+            graph.fit_generator(generate_arrays_from_file('/my_file.txt'),
+                                samples_per_epoch=10000, nb_epoch=10)
+        ```
+        '''
+        if 'show_accuracy' in kwargs:
+            kwargs.pop('show_accuracy')
+            warnings.warn('The "show_accuracy" argument is deprecated, '
+                          'instead you should pass the "accuracy" metric to '
+                          'the model at compile time:\n'
+                          '`model.compile(optimizer, loss, '
+                          'metrics=["accuracy"])`')
+        if 'nb_worker' in kwargs:
+            kwargs.pop('nb_worker')
+            warnings.warn('The "nb_worker" argument is deprecated, '
+                          'please remove it from your code.')
+        if 'nb_val_worker' in kwargs:
+            kwargs.pop('nb_val_worker')
+            warnings.warn('The "nb_val_worker" argument is deprecated, '
+                          'please remove it from your code.')
+        if kwargs:
+            raise Exception('Received unknown keyword arguments: ' +
+                            str(kwargs))
+
+        self._train_on_batch = self.train_on_batch
+        self.train_on_batch = super(Graph, self).train_on_batch
+        self._evaluate = self.evaluate
+        self.evaluate = super(Graph, self).evaluate
+
+        if validation_data and type(validation_data) is tuple:
+            raise Exception('Cannot use sample_weight with '
+                            'validation_data in legacy Graph model.')
+        if validation_data and type(validation_data) is dict:
+            validation_data = (self._get_x(validation_data),
+                               self._get_y(validation_data))
+
+        original_generator = generator
+
+        def fixed_generator():
+            while 1:
+                data = next(original_generator)
+                if type(data) is tuple:
+                    data, sample_weight = data
+                    x = self._get_x(data)
+                    y = self._get_y(data)
+                    yield x, y, sample_weight
+                else:
+                    x = self._get_x(data)
+                    y = self._get_y(data)
+                    yield x, y
+
+        generator = fixed_generator()
+        history = super(Graph, self).fit_generator(generator,
+                                                   samples_per_epoch,
+                                                   nb_epoch,
+                                                   verbose=verbose,
+                                                   callbacks=callbacks,
+                                                   validation_data=validation_data,
+                                                   nb_val_samples=nb_val_samples,
+                                                   class_weight=class_weight,
+                                                   max_q_size=max_q_size)
+        self.train_on_batch = self._train_on_batch
+        self.evaluate = self._evaluate
+        return history
+
+    def evaluate_generator(self, generator, val_samples,
+                           verbose=1, max_q_size=10, **kwargs):
+        '''Evaluates the model on a generator. The generator should
+        return the same kind of data with every yield as accepted
+        by `evaluate`.
+
+        If `show_accuracy`, it returns a tuple `(loss, accuracy)`,
+        otherwise it returns the loss value.
+
+        Arguments:
+            generator:
+                generator yielding dictionaries of the kind accepted
+                by `evaluate`, or tuples of such dictionaries and
+                associated dictionaries of sample weights.
+            val_samples:
+                total number of samples to generate from `generator`
+                to use in validation.
+
+            Other arguments are the same as for `fit`.
+        '''
+        if 'show_accuracy' in kwargs:
+            kwargs.pop('show_accuracy')
+            warnings.warn('The "show_accuracy" argument is deprecated, '
+                          'instead you should pass the "accuracy" metric to '
+                          'the model at compile time:\n'
+                          '`model.compile(optimizer, loss, '
+                          'metrics=["accuracy"])`')
+        if 'verbose' in kwargs:
+            kwargs.pop('verbose')
+            warnings.warn('The "verbose" argument is deprecated.')
+        if kwargs:
+            raise Exception('Received unknown keyword arguments: ' +
+                            str(kwargs))
+
+        self._test_on_batch = self.test_on_batch
+        self.test_on_batch = super(Graph, self).test_on_batch
+
+        original_generator = generator
+
+        def fixed_generator():
+            while 1:
+                data = next(original_generator)
+                if type(data) is tuple:
+                    data, sample_weight = data
+                    x = self._get_x(data)
+                    y = self._get_y(data)
+                    yield x, y, sample_weight
+                else:
+                    x = self._get_x(data)
+                    y = self._get_y(data)
+                    yield x, y
+
+        generator = fixed_generator()
+        history = super(Graph, self).evaluate_generator(generator,
+                                                        val_samples,
+                                                        max_q_size=max_q_size)
+        self.test_on_batch = self._test_on_batch
+        return history
+
+    # get_weights, set_weights: inherited
+    def get_config(self):
+        config = {'input_config': self._graph_input_config,
+                  'node_config': self._graph_node_config,
+                  'output_config': self._graph_output_config}
+        nodes = {}
+        for name, node in self._graph_nodes.items():
+            nodes[name] = {'class_name': node.__class__.__name__,
+                           'config': node.get_config()}
+            if name in self._graph_shared_nodes_names:
+                nodes[name]['shared'] = True
+        config['nodes'] = nodes
+        return copy.deepcopy(config)
+
+    @classmethod
+    def from_config(cls, config):
+        # TODO: test legacy support
+        from keras.utils.layer_utils import layer_from_config
+
+        def normalize_legacy_config(conf):
+            if 'class_name' not in conf:
+                class_name = conf['name']
+                name = conf.get('custom_name')
+                conf['name'] = name
+                new_config = {
+                    'class_name': class_name,
+                    'config': conf,
+                }
+                return new_config
+            return conf
+
+        graph = cls()
+        inputs = config.get('input_config')
+        for input in inputs:
+            graph.add_input(**input)
+
+        nodes = config.get('node_config')
+        for node in nodes:
+            layer_config = config['nodes'][node['name']]
+            layer_config = normalize_legacy_config(layer_config)
+            if 'layer' in node:
+                # for add_shared_node
+                node['layer'] = layer_from_config(node['layer'])
+            else:
+                layer = layer_from_config(layer_config)
+                node['layer'] = layer
+
+            node['create_output'] = False  # outputs will be added below
+            if layer_config.get('shared'):
+                graph.add_shared_node(**node)
+            else:
+                graph.add_node(**node)
+
+        outputs = config.get('output_config')
+        for output in outputs:
+            graph.add_output(**output)
+        return graph
+
+    def load_weights(self, fname):
+        if not self.built:
+            self.build()
+        super(Graph, self).load_weights(fname)

keras/metrics.py

@@ -0,0 +1,84 @@
+import numpy as np
+from . import backend as K
+
+
+def binary_accuracy(y_true, y_pred):
+    return K.mean(K.equal(y_true, K.round(y_pred)))
+
+
+def categorical_accuracy(y_true, y_pred):
+    return K.mean(K.equal(K.argmax(y_true, axis=-1),
+                  K.argmax(y_pred, axis=-1)))
+
+
+def sparse_categorical_accuracy(y_true, y_pred):
+    return K.mean(K.equal(K.max(y_true, axis=-1),
+                          K.cast(K.argmax(y_pred, axis=-1), K.floatx())))
+
+
+def mean_squared_error(y_true, y_pred):
+    return K.mean(K.square(y_pred - y_true))
+
+
+def mean_absolute_error(y_true, y_pred):
+    return K.mean(K.abs(y_pred - y_true))
+
+
+def mean_absolute_percentage_error(y_true, y_pred):
+    diff = K.abs((y_true - y_pred) / K.clip(K.abs(y_true), K.epsilon(), np.inf))
+    return 100. * K.mean(diff)
+
+
+def mean_squared_logarithmic_error(y_true, y_pred):
+    first_log = K.log(K.clip(y_pred, K.epsilon(), np.inf) + 1.)
+    second_log = K.log(K.clip(y_true, K.epsilon(), np.inf) + 1.)
+    return K.mean(K.square(first_log - second_log))
+
+
+def squared_hinge(y_true, y_pred):
+    return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)))
+
+
+def hinge(y_true, y_pred):
+    return K.mean(K.maximum(1. - y_true * y_pred, 0.))
+
+
+def categorical_crossentropy(y_true, y_pred):
+    '''Expects a binary class matrix instead of a vector of scalar classes.
+    '''
+    return K.mean(K.categorical_crossentropy(y_pred, y_true))
+
+
+def sparse_categorical_crossentropy(y_true, y_pred):
+    '''expects an array of integer classes.
+    Note: labels shape must have the same number of dimensions as output shape.
+    If you get a shape error, add a length-1 dimension to labels.
+    '''
+    return K.mean(K.sparse_categorical_crossentropy(y_pred, y_true))
+
+
+def binary_crossentropy(y_true, y_pred):
+    return K.mean(K.binary_crossentropy(y_pred, y_true))
+
+
+def poisson(y_true, y_pred):
+    return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()))
+
+
+def cosine_proximity(y_true, y_pred):
+    y_true = K.l2_normalize(y_true, axis=-1)
+    y_pred = K.l2_normalize(y_pred, axis=-1)
+    return -K.mean(y_true * y_pred)
+
+
+# aliases
+mse = MSE = mean_squared_error
+mae = MAE = mean_absolute_error
+mape = MAPE = mean_absolute_percentage_error
+msle = MSLE = mean_squared_logarithmic_error
+cosine = cosine_proximity
+
+
+from .utils.generic_utils import get_from_module
+def get(identifier):
+    return get_from_module(identifier, globals(), 'metric')

keras/objectives.py

@@ -36,6 +36,14 @@ def categorical_crossentropy(y_true, y_pred):
     return K.categorical_crossentropy(y_pred, y_true)
 
 
+def sparse_categorical_crossentropy(y_true, y_pred):
+    '''expects an array of integer classes.
+    Note: labels shape must have the same number of dimensions as output shape.
+    If you get a shape error, add a length-1 dimension to labels.
+    '''
+    return K.sparse_categorical_crossentropy(y_pred, y_true)
+
+
 def binary_crossentropy(y_true, y_pred):
     return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
 

keras/optimizers.py

@@ -29,8 +29,14 @@ class Optimizer(object):
             when their absolute value exceeds this value.
     '''
     def __init__(self, **kwargs):
+        allowed_kwargs = {'clipnorm', 'clipvalue'}
+        for k in kwargs:
+            if k not in allowed_kwargs:
+                raise Exception('Unexpected keyword argument '
+                                'passed to optimizer: ' + str(k))
         self.__dict__.update(kwargs)
         self.updates = []
+        self.weights = []
 
     def get_state(self):
         return [K.get_value(u[0]) for u in self.updates]
@@ -52,13 +58,53 @@ class Optimizer(object):
             grads = [K.clip(g, -self.clipvalue, self.clipvalue) for g in grads]
         return grads
 
+    def set_weights(self, weights):
+        '''Sets the weights of the optimizer, from Numpy arrays.
+
+        Should only be called after computing the gradients
+        (otherwise the optimizer has no weights).
+
+        # Arguments
+            weights: a list of Numpy arrays. The number
+                of arrays and their shape must match
+                number of the dimensions of the weights
+                of the optimizer (i.e. it should match the
+                output of `get_weights`).
+        '''
+        params = self.weights
+        if len(params) != len(weights):
+            raise Exception('Provided weight array does not match  weights (' +
+                            str(len(params)) + ' optimizer params vs. ' +
+                            str(len(weights)) + ' provided weights)')
+        for p, w in zip(params, weights):
+            if K.get_value(p).shape != w.shape:
+                raise Exception('Optimizer weight shape ' +
+                                str(K.get_value(p).shape) +
+                                ' not compatible with '
+                                'provided weight shape ' + str(w.shape))
+            K.set_value(p, w)
+
+    def get_weights(self):
+        '''Returns the current weights of the optimizer,
+        as a list of numpy arrays.
+        '''
+        weights = []
+        for p in self.weights:
+            weights.append(K.get_value(p))
+        return weights
+
     def get_config(self):
-        return {"name": self.__class__.__name__}
+        config = {'name': self.__class__.__name__}
+        if hasattr(self, 'clipnorm'):
+            config['clipnorm'] = self.clipnorm
+        if hasattr(self, 'clipvalue'):
+            config['clipvalue'] = self.clipvalue
+        return config
 
 
 class SGD(Optimizer):
     '''Stochastic gradient descent, with support for momentum,
-    decay, and Nesterov momentum.
+    learning rate decay, and Nesterov momentum.
 
     # Arguments
         lr: float >= 0. Learning rate.
@@ -66,8 +112,8 @@ class SGD(Optimizer):
         decay: float >= 0. Learning rate decay over each update.
         nesterov: boolean. Whether to apply Nesterov momentum.
     '''
-    def __init__(self, lr=0.01, momentum=0., decay=0., nesterov=False,
-                 *args, **kwargs):
+    def __init__(self, lr=0.01, momentum=0., decay=0.,
+                 nesterov=False, **kwargs):
         super(SGD, self).__init__(**kwargs)
         self.__dict__.update(locals())
         self.iterations = K.variable(0.)
@@ -77,11 +123,12 @@ class SGD(Optimizer):
 
     def get_updates(self, params, constraints, loss):
         grads = self.get_gradients(loss, params)
-        lr = self.lr * (1.0 / (1.0 + self.decay * self.iterations))
+        lr = self.lr * (1. / (1. + self.decay * self.iterations))
         self.updates = [(self.iterations, self.iterations + 1.)]
 
-        for p, g, c in zip(params, grads, constraints):
-            m = K.variable(np.zeros(K.get_value(p).shape))  # momentum
+        # momentum
+        self.weights = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
+        for p, g, m in zip(params, grads, self.weights):
             v = self.momentum * m - lr * g  # velocity
             self.updates.append((m, v))
 
@@ -90,22 +137,28 @@ class SGD(Optimizer):
             else:
                 new_p = p + v
 
-            self.updates.append((p, c(new_p)))  # apply constraints
+            # apply constraints
+            if p in constraints:
+                c = constraints[p]
+                new_p = c(new_p)
+            self.updates.append((p, new_p))
         return self.updates
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "lr": float(K.get_value(self.lr)),
-                "momentum": float(K.get_value(self.momentum)),
-                "decay": float(K.get_value(self.decay)),
-                "nesterov": self.nesterov}
+        config = {'lr': float(K.get_value(self.lr)),
+                  'momentum': float(K.get_value(self.momentum)),
+                  'decay': float(K.get_value(self.decay)),
+                  'nesterov': self.nesterov}
+        base_config = super(SGD, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))
 
 
 class RMSprop(Optimizer):
     '''RMSProp optimizer.
 
     It is recommended to leave the parameters of this optimizer
-    at their default values.
+    at their default values
+    (except the learning rate, which can be freely tuned).
 
     This optimizer is usually a good choice for recurrent
     neural networks.
@@ -115,7 +168,7 @@ class RMSprop(Optimizer):
         rho: float >= 0.
         epsilon: float >= 0. Fuzz factor.
     '''
-    def __init__(self, lr=0.001, rho=0.9, epsilon=1e-6, *args, **kwargs):
+    def __init__(self, lr=0.001, rho=0.9, epsilon=1e-8, **kwargs):
         super(RMSprop, self).__init__(**kwargs)
         self.__dict__.update(locals())
         self.lr = K.variable(lr)
@@ -123,23 +176,29 @@ class RMSprop(Optimizer):
 
     def get_updates(self, params, constraints, loss):
         grads = self.get_gradients(loss, params)
-        accumulators = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
+        # accumulators
+        self.weights = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
         self.updates = []
 
-        for p, g, a, c in zip(params, grads, accumulators, constraints):
+        for p, g, a in zip(params, grads, self.weights):
             # update accumulator
-            new_a = self.rho * a + (1 - self.rho) * K.square(g)
+            new_a = self.rho * a + (1. - self.rho) * K.square(g)
             self.updates.append((a, new_a))
+            new_p = p - self.lr * g / (K.sqrt(new_a) + self.epsilon)
 
-            new_p = p - self.lr * g / K.sqrt(new_a + self.epsilon)
-            self.updates.append((p, c(new_p)))  # apply constraints
+            # apply constraints
+            if p in constraints:
+                c = constraints[p]
+                new_p = c(new_p)
+            self.updates.append((p, new_p))
         return self.updates
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "lr": float(K.get_value(self.lr)),
-                "rho": float(K.get_value(self.rho)),
-                "epsilon": self.epsilon}
+        config = {'lr': float(K.get_value(self.lr)),
+                  'rho': float(K.get_value(self.rho)),
+                  'epsilon': self.epsilon}
+        base_config = super(RMSprop, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))
 
 
 class Adagrad(Optimizer):
@@ -152,27 +211,33 @@ class Adagrad(Optimizer):
         lr: float >= 0. Learning rate.
         epsilon: float >= 0.
     '''
-    def __init__(self, lr=0.01, epsilon=1e-6, *args, **kwargs):
+    def __init__(self, lr=0.01, epsilon=1e-8, **kwargs):
         super(Adagrad, self).__init__(**kwargs)
         self.__dict__.update(locals())
         self.lr = K.variable(lr)
 
     def get_updates(self, params, constraints, loss):
         grads = self.get_gradients(loss, params)
-        accumulators = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
+        # accumulators
+        self.weights = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
         self.updates = []
 
-        for p, g, a, c in zip(params, grads, accumulators, constraints):
+        for p, g, a in zip(params, grads, self.weights):
             new_a = a + K.square(g)  # update accumulator
             self.updates.append((a, new_a))
-            new_p = p - self.lr * g / K.sqrt(new_a + self.epsilon)
-            self.updates.append((p, c(new_p)))  # apply constraints
+            new_p = p - self.lr * g / (K.sqrt(new_a) + self.epsilon)
+            # apply constraints
+            if p in constraints:
+                c = constraints[p]
+                new_p = c(new_p)
+            self.updates.append((p, new_p))
         return self.updates
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "lr": float(K.get_value(self.lr)),
-                "epsilon": self.epsilon}
+        config = {'lr': float(K.get_value(self.lr)),
+                  'epsilon': self.epsilon}
+        base_config = super(Adagrad, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))
 
 
 class Adadelta(Optimizer):
@@ -182,14 +247,15 @@ class Adadelta(Optimizer):
     at their default values.
 
     # Arguments
-        lr: float >= 0. Learning rate. It is recommended to leave it at the default value.
+        lr: float >= 0. Learning rate.
+            It is recommended to leave it at the default value.
         rho: float >= 0.
         epsilon: float >= 0. Fuzz factor.
 
     # References
         - [Adadelta - an adaptive learning rate method](http://arxiv.org/abs/1212.5701)
     '''
-    def __init__(self, lr=1.0, rho=0.95, epsilon=1e-6, *args, **kwargs):
+    def __init__(self, lr=1.0, rho=0.95, epsilon=1e-8, **kwargs):
         super(Adadelta, self).__init__(**kwargs)
         self.__dict__.update(locals())
         self.lr = K.variable(lr)
@@ -198,19 +264,23 @@ class Adadelta(Optimizer):
         grads = self.get_gradients(loss, params)
         accumulators = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
         delta_accumulators = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
+        self.weights = accumulators + delta_accumulators
         self.updates = []
 
-        for p, g, a, d_a, c in zip(params, grads, accumulators,
-                                   delta_accumulators, constraints):
+        for p, g, a, d_a in zip(params, grads, accumulators, delta_accumulators):
             # update accumulator
-            new_a = self.rho * a + (1 - self.rho) * K.square(g)
+            new_a = self.rho * a + (1. - self.rho) * K.square(g)
             self.updates.append((a, new_a))
 
             # use the new accumulator and the *old* delta_accumulator
             update = g * K.sqrt(d_a + self.epsilon) / K.sqrt(new_a + self.epsilon)
 
             new_p = p - self.lr * update
-            self.updates.append((p, c(new_p)))  # apply constraints
+            # apply constraints
+            if p in constraints:
+                c = constraints[p]
+                new_p = c(new_p)
+            self.updates.append((p, new_p))
 
             # update delta_accumulator
             new_d_a = self.rho * d_a + (1 - self.rho) * K.square(update)
@@ -218,10 +288,11 @@ class Adadelta(Optimizer):
         return self.updates
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "lr": float(K.get_value(self.lr)),
-                "rho": self.rho,
-                "epsilon": self.epsilon}
+        config = {'lr': float(K.get_value(self.lr)),
+                  'rho': self.rho,
+                  'epsilon': self.epsilon}
+        base_config = super(Adadelta, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))
 
 
 class Adam(Optimizer):
@@ -237,8 +308,8 @@ class Adam(Optimizer):
     # References
         - [Adam - A Method for Stochastic Optimization](http://arxiv.org/abs/1412.6980v8)
     '''
-    def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-8,
-                 *args, **kwargs):
+    def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999,
+                 epsilon=1e-8, **kwargs):
         super(Adam, self).__init__(**kwargs)
         self.__dict__.update(locals())
         self.iterations = K.variable(0)
@@ -248,32 +319,38 @@ class Adam(Optimizer):
 
     def get_updates(self, params, constraints, loss):
         grads = self.get_gradients(loss, params)
-        self.updates = [(self.iterations, self.iterations+1.)]
+        self.updates = [(self.iterations, self.iterations + 1)]
 
         t = self.iterations + 1
-        lr_t = self.lr * K.sqrt(1 - K.pow(self.beta_2, t)) / (1 - K.pow(self.beta_1, t))
+        lr_t = self.lr * K.sqrt(1. - K.pow(self.beta_2, t)) / (1. - K.pow(self.beta_1, t))
 
-        for p, g, c in zip(params, grads, constraints):
-            # zero init of moment
-            m = K.variable(np.zeros(K.get_value(p).shape))
-            # zero init of velocity
-            v = K.variable(np.zeros(K.get_value(p).shape))
+        ms = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
+        vs = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
+        self.weights = ms + vs
 
-            m_t = (self.beta_1 * m) + (1 - self.beta_1) * g
-            v_t = (self.beta_2 * v) + (1 - self.beta_2) * K.square(g)
+        for p, g, m, v in zip(params, grads, ms, vs):
+            m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
+            v_t = (self.beta_2 * v) + (1. - self.beta_2) * K.square(g)
             p_t = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon)
 
             self.updates.append((m, m_t))
             self.updates.append((v, v_t))
-            self.updates.append((p, c(p_t)))  # apply constraints
+
+            new_p = p_t
+            # apply constraints
+            if p in constraints:
+                c = constraints[p]
+                new_p = c(new_p)
+            self.updates.append((p, new_p))
         return self.updates
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "lr": float(K.get_value(self.lr)),
-                "beta_1": float(K.get_value(self.beta_1)),
-                "beta_2": float(K.get_value(self.beta_2)),
-                "epsilon": self.epsilon}
+        config = {'lr': float(K.get_value(self.lr)),
+                  'beta_1': float(K.get_value(self.beta_1)),
+                  'beta_2': float(K.get_value(self.beta_2)),
+                  'epsilon': self.epsilon}
+        base_config = super(Adam, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))
 
 
 class Adamax(Optimizer):
@@ -290,43 +367,52 @@ class Adamax(Optimizer):
     # References
         - [Adam - A Method for Stochastic Optimization](http://arxiv.org/abs/1412.6980v8)
     '''
-    def __init__(self, lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=1e-8,
-                 *args, **kwargs):
+    def __init__(self, lr=0.002, beta_1=0.9, beta_2=0.999,
+                 epsilon=1e-8, **kwargs):
         super(Adamax, self).__init__(**kwargs)
         self.__dict__.update(locals())
-        self.iterations = K.variable(0)
+        self.iterations = K.variable(0.)
         self.lr = K.variable(lr)
         self.beta_1 = K.variable(beta_1)
         self.beta_2 = K.variable(beta_2)
 
     def get_updates(self, params, constraints, loss):
         grads = self.get_gradients(loss, params)
-        self.updates = [(self.iterations, self.iterations+1.)]
+        self.updates = [(self.iterations, self.iterations + 1)]
 
         t = self.iterations + 1
-        lr_t = self.lr / (1 - K.pow(self.beta_1, t))
+        lr_t = self.lr / (1. - K.pow(self.beta_1, t))
 
-        for p, g, c in zip(params, grads, constraints):
-            # zero init of 1st moment
-            m = K.variable(np.zeros(K.get_value(p).shape))
-            # zero init of exponentially weighted infinity norm
-            u = K.variable(np.zeros(K.get_value(p).shape))
+        # zero init of 1st moment
+        ms = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
+        # zero init of exponentially weighted infinity norm
+        us = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
+        self.weights = ms + us
 
-            m_t = (self.beta_1 * m) + (1 - self.beta_1) * g
+        for p, g, m, u in zip(params, grads, ms, us):
+
+            m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
             u_t = K.maximum(self.beta_2 * u, K.abs(g))
             p_t = p - lr_t * m_t / (u_t + self.epsilon)
 
             self.updates.append((m, m_t))
             self.updates.append((u, u_t))
-            self.updates.append((p, c(p_t)))  # apply constraints
+
+            new_p = p_t
+            # apply constraints
+            if p in constraints:
+                c = constraints[p]
+                new_p = c(new_p)
+            self.updates.append((p, new_p))
         return self.updates
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "lr": float(K.get_value(self.lr)),
-                "beta_1": float(K.get_value(self.beta_1)),
-                "beta_2": float(K.get_value(self.beta_2)),
-                "epsilon": self.epsilon}
+        config = {'lr': float(K.get_value(self.lr)),
+                  'beta_1': float(K.get_value(self.beta_1)),
+                  'beta_2': float(K.get_value(self.beta_2)),
+                  'epsilon': self.epsilon}
+        base_config = super(Adamax, self).get_config()
+        return dict(list(base_config.items()) + list(config.items()))
 
 
 # aliases

keras/preprocessing/image.py

@@ -1,60 +1,75 @@
+'''Fairly basic set of tools for realtime data augmentation on image data.
+Can easily be extended to include new transformations,
+new preprocessing methods, etc...
+'''
 from __future__ import absolute_import
 
 import numpy as np
 import re
-from scipy import ndimage
 from scipy import linalg
-
-from os import listdir
-from os.path import isfile, join
-import random
-import math
+import scipy.ndimage as ndi
 from six.moves import range
+import os
 import threading
 
-'''Fairly basic set of tools for realtime data augmentation on image data.
-Can easily be extended to include new transformations, new preprocessing methods, etc...
-'''
 
+def random_rotation(x, rg, row_index=1, col_index=2, channel_index=0,
+                    fill_mode='nearest', cval=0.):
+    theta = np.pi / 180 * np.random.uniform(-rg, rg)
+    rotation_matrix = np.array([[np.cos(theta), -np.sin(theta), 0],
+                                [np.sin(theta), np.cos(theta), 0],
+                                [0, 0, 1]])
 
-def random_rotation(x, rg, fill_mode="nearest", cval=0.):
-    angle = random.uniform(-rg, rg)
-    x = ndimage.interpolation.rotate(x, angle,
-                                     axes=(1, 2),
-                                     reshape=False,
-                                     mode=fill_mode,
-                                     cval=cval)
+    h, w = x.shape[row_index], x.shape[col_index]
+    transform_matrix = transform_matrix_offset_center(rotation_matrix, h, w)
+    x = apply_transform(x, transform_matrix, channel_index, fill_mode, cval)
     return x
 
 
-def random_shift(x, wrg, hrg, fill_mode="nearest", cval=0.):
-    crop_left_pixels = 0
-    crop_top_pixels = 0
+def random_shift(x, wrg, hrg, row_index=1, col_index=2, channel_index=0,
+                 fill_mode='nearest', cval=0.):
+    h, w = x.shape[row_index], x.shape[col_index]
+    tx = np.random.uniform(-hrg, hrg) * h
+    ty = np.random.uniform(-wrg, wrg) * w
+    translation_matrix = np.array([[1, 0, tx],
+                                   [0, 1, ty],
+                                   [0, 0, 1]])
 
-    if wrg:
-        crop = random.uniform(0., wrg)
-        split = random.uniform(0, 1)
-        crop_left_pixels = int(split*crop*x.shape[1])
-    if hrg:
-        crop = random.uniform(0., hrg)
-        split = random.uniform(0, 1)
-        crop_top_pixels = int(split*crop*x.shape[2])
-    x = ndimage.interpolation.shift(x, (0, crop_left_pixels, crop_top_pixels),
-                                    order=0,
-                                    mode=fill_mode,
-                                    cval=cval)
+    transform_matrix = translation_matrix  # no need to do offset
+    x = apply_transform(x, transform_matrix, channel_index, fill_mode, cval)
     return x
 
 
-def horizontal_flip(x):
-    for i in range(x.shape[0]):
-        x[i] = np.fliplr(x[i])
+def random_shear(x, intensity, row_index=1, col_index=2, channel_index=0,
+                 fill_mode='nearest', cval=0.):
+    shear = np.random.uniform(-intensity, intensity)
+    shear_matrix = np.array([[1, -np.sin(shear), 0],
+                             [0, np.cos(shear), 0],
+                             [0, 0, 1]])
+
+    h, w = x.shape[row_index], x.shape[col_index]
+    transform_matrix = transform_matrix_offset_center(shear_matrix, h, w)
+    x = apply_transform(x, transform_matrix, channel_index, fill_mode, cval)
     return x
 
 
-def vertical_flip(x):
-    for i in range(x.shape[0]):
-        x[i] = np.flipud(x[i])
+def random_zoom(x, zoom_range, row_index=1, col_index=2, channel_index=0,
+                fill_mode='nearest', cval=0.):
+    if len(zoom_range) != 2:
+        raise Exception('zoom_range should be a tuple or list of two floats. '
+                        'Received arg: ', zoom_range)
+
+    if zoom_range[0] == 1 and zoom_range[1] == 1:
+        zx, zy = 1, 1
+    else:
+        zx, zy = np.random.uniform(zoom_range[0], zoom_range[1], 2)
+    zoom_matrix = np.array([[zx, 0, 0],
+                            [0, zy, 0],
+                            [0, 0, 1]])
+
+    h, w = x.shape[row_index], x.shape[col_index]
+    transform_matrix = transform_matrix_offset_center(zoom_matrix, h, w)
+    x = apply_transform(x, transform_matrix, channel_index, fill_mode, cval)
     return x
 
 
@@ -63,55 +78,77 @@ def random_barrel_transform(x, intensity):
     pass
 
 
-def random_shear(x, intensity, fill_mode="nearest", cval=0.):
-    shear = random.uniform(-intensity, intensity)
-    shear_matrix = np.array([[1.0, -math.sin(shear), 0.0],
-                            [0.0, math.cos(shear), 0.0],
-                            [0.0, 0.0, 1.0]])
-    x = ndimage.interpolation.affine_transform(x, shear_matrix,
-                                               mode=fill_mode,
-                                               order=3,
-                                               cval=cval)
+def random_channel_shift(x, intensity, channel_index=0):
+    x = np.rollaxis(x, channel_index, 0)
+    min_x, max_x = np.min(x), np.max(x)
+    channel_images = [np.clip(x_channel + np.random.uniform(-intensity, intensity), min_x, max_x)
+                      for x_channel in x]
+    x = np.stack(channel_images, axis=0)
+    x = np.rollaxis(x, 0, channel_index+1)
     return x
 
 
-def random_channel_shift(x, rg):
-    # TODO
-    pass
+def transform_matrix_offset_center(matrix, x, y):
+    o_x = float(x) / 2 + 0.5
+    o_y = float(y) / 2 + 0.5
+    offset_matrix = np.array([[1, 0, o_x], [0, 1, o_y], [0, 0, 1]])
+    reset_matrix = np.array([[1, 0, -o_x], [0, 1, -o_y], [0, 0, 1]])
+    transform_matrix = np.dot(np.dot(offset_matrix, matrix), reset_matrix)
+    return transform_matrix
 
 
-def random_zoom(x, rg, fill_mode="nearest", cval=0.):
-    zoom_w = random.uniform(1.-rg, 1.)
-    zoom_h = random.uniform(1.-rg, 1.)
-    x = ndimage.interpolation.zoom(x, zoom=(1., zoom_w, zoom_h),
-                                   mode=fill_mode,
-                                   cval=cval)
-    return x  # shape of result will be different from shape of input!
+def apply_transform(x, transform_matrix, channel_index=0, fill_mode='nearest', cval=0.):
+    x = np.rollaxis(x, channel_index, 0)
+    final_affine_matrix = transform_matrix[:2, :2]
+    final_offset = transform_matrix[:2, 2]
+    channel_images = [ndi.interpolation.affine_transform(x_channel, final_affine_matrix,
+                      final_offset, order=0, mode=fill_mode, cval=cval) for x_channel in x]
+    x = np.stack(channel_images, axis=0)
+    x = np.rollaxis(x, 0, channel_index+1)
+    return x
 
 
-def array_to_img(x, scale=True):
+def flip_axis(x, axis):
+    x = np.asarray(x).swapaxes(axis, 0)
+    x = x[::-1, ...]
+    x = x.swapaxes(0, axis)
+    return x
+
+
+def array_to_img(x, dim_ordering='th', scale=True):
     from PIL import Image
-    x = x.transpose(1, 2, 0)
+    if dim_ordering == 'th':
+        x = x.transpose(1, 2, 0)
     if scale:
         x += max(-np.min(x), 0)
         x /= np.max(x)
         x *= 255
     if x.shape[2] == 3:
         # RGB
-        return Image.fromarray(x.astype("uint8"), "RGB")
-    else:
+        return Image.fromarray(x.astype('uint8'), 'RGB')
+    elif x.shape[2] == 1:
         # grayscale
-        return Image.fromarray(x[:, :, 0].astype("uint8"), "L")
+        return Image.fromarray(x[:, :, 0].astype('uint8'), 'L')
+    else:
+        raise Exception('Unsupported channel number: ', x.shape[2])
 
 
-def img_to_array(img):
+# only used by tests/keras/preprocessing/test_image.py to convert PIL.Image to numpy array
+def img_to_array(img, dim_ordering='th'):
+    if dim_ordering not in ['th', 'tf']:
+        raise Exception('Unknown dim_ordering: ', dim_ordering)
+    # image has dim_ordering (height, width, channel)
     x = np.asarray(img, dtype='float32')
     if len(x.shape) == 3:
-        # RGB: height, width, channel -> channel, height, width
-        x = x.transpose(2, 0, 1)
+        if dim_ordering == 'th':
+            x = x.transpose(2, 0, 1)
+    elif len(x.shape) == 2:
+        if dim_ordering == 'th':
+            x = x.reshape((1, x.shape[0], x.shape[1]))
+        else:
+            x = x.reshape((x.shape[0], x.shape[1], 1))
     else:
-        # grayscale: height, width -> channel, height, width
-        x = x.reshape((1, x.shape[0], x.shape[1]))
+        raise Exception('Unsupported image shape: ', x.shape)
     return x
 
 
@@ -126,77 +163,135 @@ def load_img(path, grayscale=False):
 
 
 def list_pictures(directory, ext='jpg|jpeg|bmp|png'):
-    return [join(directory, f) for f in listdir(directory)
-            if isfile(join(directory, f)) and re.match('([\w]+\.(?:' + ext + '))', f)]
+    return [os.path.join(directory, f) for f in os.listdir(directory)
+            if os.path.isfile(os.path.join(directory, f)) and re.match('([\w]+\.(?:' + ext + '))', f)]
 
 
 class ImageDataGenerator(object):
     '''Generate minibatches with
-    realtime data augmentation.
+    real-time data augmentation.
+
+    # Arguments
+        featurewise_center: set input mean to 0 over the dataset.
+        samplewise_center: set each sample mean to 0.
+        featurewise_std_normalization: divide inputs by std of the dataset.
+        samplewise_std_normalization: divide each input by its std.
+        zca_whitening: apply ZCA whitening.
+        rotation_range: degrees (0 to 180).
+        width_shift_range: fraction of total width.
+        height_shift_range: fraction of total height.
+        shear_range: shear intensity (shear angle in radians).
+        zoom_range: amount of zoom. if scalar z, zoom will be randomly picked
+            in the range [1-z, 1+z]. A sequence of two can be passed instead
+            to select this range.
+        channel_shift_range: shift range for each channels.
+        fill_mode: points outside the boundaries are filled according to the
+            given mode ('constant', 'nearest', 'reflect' or 'wrap'). Default
+            is 'nearest'.
+        cval: value used for points outside the boundaries when fill_mode is
+            'constant'. Default is 0.
+        horizontal_flip: whether to randomly flip images horizontally.
+        vertical_flip: whether to randomly flip images vertically.
+        dim_ordering: 'th' or 'tf'. In 'th' mode, the channels dimension
+            (the depth) is at index 1, in 'tf' mode it is at index 3.
     '''
     def __init__(self,
-                 featurewise_center=True,  # set input mean to 0 over the dataset
-                 samplewise_center=False,  # set each sample mean to 0
-                 featurewise_std_normalization=True,  # divide inputs by std of the dataset
-                 samplewise_std_normalization=False,  # divide each input by its std
-                 zca_whitening=False,  # apply ZCA whitening
-                 rotation_range=0.,  # degrees (0 to 180)
-                 width_shift_range=0.,  # fraction of total width
-                 height_shift_range=0.,  # fraction of total height
-                 shear_range=0.,  # shear intensity (shear angle in radians)
+                 featurewise_center=False,
+                 samplewise_center=False,
+                 featurewise_std_normalization=False,
+                 samplewise_std_normalization=False,
+                 zca_whitening=False,
+                 rotation_range=0.,
+                 width_shift_range=0.,
+                 height_shift_range=0.,
+                 shear_range=0.,
+                 zoom_range=0.,
+                 channel_shift_range=0.,
+                 fill_mode='nearest',
+                 cval=0.,
                  horizontal_flip=False,
-                 vertical_flip=False):
-
+                 vertical_flip=False,
+                 dim_ordering='th'):
         self.__dict__.update(locals())
         self.mean = None
         self.std = None
         self.principal_components = None
         self.lock = threading.Lock()
 
+        if dim_ordering not in {'tf', 'th'}:
+            raise Exception('dim_ordering should be "tf" (channel after row and '
+                            'column) or "th" (channel before row and column). '
+                            'Received arg: ', dim_ordering)
+        self.dim_ordering = dim_ordering
+        if dim_ordering == "th":
+            self.channel_index = 1
+            self.row_index = 2
+            self.col_index = 3
+        if dim_ordering == "tf":
+            self.channel_index = 3
+            self.row_index = 1
+            self.col_index = 2
+
+        if np.isscalar(zoom_range):
+            self.zoom_range = [1 - zoom_range, 1 + zoom_range]
+        elif len(zoom_range) == 2:
+            self.zoom_range = [zoom_range[0], zoom_range[1]]
+        else:
+            raise Exception('zoom_range should be a float or '
+                            'a tuple or list of two floats. '
+                            'Received arg: ', zoom_range)
+
+        self.batch_index = 0
+        self.total_batches_seen = 0
+
+    def reset(self):
+        self.batch_index = 0
+
     def _flow_index(self, N, batch_size=32, shuffle=False, seed=None):
-        b = 0
-        total_b = 0
+        # ensure self.batch_index is 0
+        self.reset()
+
         while 1:
-            if b == 0:
-                if seed is not None:
-                    np.random.seed(seed + total_b)
-
+            if self.batch_index == 0:
+                index_array = np.arange(N)
                 if shuffle:
+                    if seed is not None:
+                        np.random.seed(seed + self.total_batches_seen)
                     index_array = np.random.permutation(N)
-                else:
-                    index_array = np.arange(N)
 
-            current_index = (b * batch_size) % N
+            current_index = (self.batch_index * batch_size) % N
             if N >= current_index + batch_size:
                 current_batch_size = batch_size
+                self.batch_index += 1
             else:
                 current_batch_size = N - current_index
-
-            if current_batch_size == batch_size:
-                b += 1
-            else:
-                b = 0
-            total_b += 1
-            yield index_array[current_index: current_index + current_batch_size], current_index, current_batch_size
+                self.batch_index = 0
+            self.total_batches_seen += 1
+            yield (index_array[current_index: current_index + current_batch_size],
+                   current_index, current_batch_size)
 
     def flow(self, X, y, batch_size=32, shuffle=False, seed=None,
-             save_to_dir=None, save_prefix="", save_format="jpeg"):
+             save_to_dir=None, save_prefix='', save_format='jpeg'):
         assert len(X) == len(y)
         self.X = X
         self.y = y
         self.save_to_dir = save_to_dir
         self.save_prefix = save_prefix
         self.save_format = save_format
-        self.flow_generator = self._flow_index(X.shape[0], batch_size, shuffle, seed)
+        self.reset()
+        self.flow_generator = self._flow_index(X.shape[0], batch_size,
+                                               shuffle, seed)
         return self
 
     def __iter__(self):
-        # needed if we want to do something like for x,y in data_gen.flow(...):
+        # needed if we want to do something like:
+        # for x, y in data_gen.flow(...):
         return self
 
     def next(self):
-        # for python 2.x
-        # Keep under lock only the mechainsem which advance the indexing of each batch
+        # for python 2.x.
+        # Keeps under lock only the mechanism which advances
+        # the indexing of each batch
         # see # http://anandology.com/blog/using-iterators-and-generators/
         with self.lock:
             index_array, current_index, current_batch_size = next(self.flow_generator)
@@ -204,93 +299,148 @@ class ImageDataGenerator(object):
         bX = np.zeros(tuple([current_batch_size] + list(self.X.shape)[1:]))
         for i, j in enumerate(index_array):
             x = self.X[j]
-            x = self.random_transform(x.astype("float32"))
+            x = self.random_transform(x.astype('float32'))
             x = self.standardize(x)
             bX[i] = x
         if self.save_to_dir:
             for i in range(current_batch_size):
-                img = array_to_img(bX[i], scale=True)
-                img.save(self.save_to_dir + "/" + self.save_prefix + "_" + str(current_index + i) + "." + self.save_format)
+                img = array_to_img(bX[i], self.dim_ordering, scale=True)
+                fname = '{prefix}_{index}.{format}'.format(prefix=self.save_prefix,
+                                                           index=current_index + i,
+                                                           format=self.save_format)
+                img.save(os.path.join(self.save_to_dir, fname))
         bY = self.y[index_array]
         return bX, bY
 
     def __next__(self):
-        # for python 3.x
+        # for python 3.x.
         return self.next()
 
     def standardize(self, x):
+        # x is a single image, so it doesn't have image number at index 0
+        img_channel_index = self.channel_index - 1
+        if self.samplewise_center:
+            x -= np.mean(x, axis=img_channel_index, keepdims=True)
+        if self.samplewise_std_normalization:
+            x /= (np.std(x, axis=img_channel_index, keepdims=True) + 1e-7)
+
         if self.featurewise_center:
             x -= self.mean
         if self.featurewise_std_normalization:
-            x /= self.std
+            x /= (self.std + 1e-7)
 
         if self.zca_whitening:
-            flatx = np.reshape(x, (x.shape[0]*x.shape[1]*x.shape[2]))
+            flatx = np.reshape(x, (x.size))
             whitex = np.dot(flatx, self.principal_components)
             x = np.reshape(whitex, (x.shape[0], x.shape[1], x.shape[2]))
 
-        if self.samplewise_center:
-            x -= np.mean(x)
-        if self.samplewise_std_normalization:
-            x /= np.std(x)
-
         return x
 
     def random_transform(self, x):
+        # x is a single image, so it doesn't have image number at index 0
+        img_row_index = self.row_index - 1
+        img_col_index = self.col_index - 1
+        img_channel_index = self.channel_index - 1
+
+        # use composition of homographies to generate final transform that needs to be applied
         if self.rotation_range:
-            x = random_rotation(x, self.rotation_range)
-        if self.width_shift_range or self.height_shift_range:
-            x = random_shift(x, self.width_shift_range, self.height_shift_range)
-        if self.horizontal_flip:
-            if random.random() < 0.5:
-                x = horizontal_flip(x)
-        if self.vertical_flip:
-            if random.random() < 0.5:
-                x = vertical_flip(x)
+            theta = np.pi / 180 * np.random.uniform(-self.rotation_range, self.rotation_range)
+        else:
+            theta = 0
+        rotation_matrix = np.array([[np.cos(theta), -np.sin(theta), 0],
+                                    [np.sin(theta), np.cos(theta), 0],
+                                    [0, 0, 1]])
+        if self.height_shift_range:
+            tx = np.random.uniform(-self.height_shift_range, self.height_shift_range) * x.shape[img_row_index]
+        else:
+            tx = 0
+
+        if self.width_shift_range:
+            ty = np.random.uniform(-self.width_shift_range, self.width_shift_range) * x.shape[img_col_index]
+        else:
+            ty = 0
+
+        translation_matrix = np.array([[1, 0, tx],
+                                       [0, 1, ty],
+                                       [0, 0, 1]])
         if self.shear_range:
-            x = random_shear(x,self.shear_range)
+            shear = np.random.uniform(-self.shear_range, self.shear_range)
+        else:
+            shear = 0
+        shear_matrix = np.array([[1, -np.sin(shear), 0],
+                                 [0, np.cos(shear), 0],
+                                 [0, 0, 1]])
+
+        if self.zoom_range[0] == 1 and self.zoom_range[1] == 1:
+            zx, zy = 1, 1
+        else:
+            zx, zy = np.random.uniform(self.zoom_range[0], self.zoom_range[1], 2)
+        zoom_matrix = np.array([[zx, 0, 0],
+                                [0, zy, 0],
+                                [0, 0, 1]])
+
+        transform_matrix = np.dot(np.dot(np.dot(rotation_matrix, translation_matrix), shear_matrix), zoom_matrix)
+
+        h, w = x.shape[img_row_index], x.shape[img_col_index]
+        transform_matrix = transform_matrix_offset_center(transform_matrix, h, w)
+        x = apply_transform(x, transform_matrix, img_channel_index,
+                            fill_mode=self.fill_mode, cval=self.cval)
+        if self.channel_shift_range != 0:
+            x = random_channel_shift(x, self.channel_shift_range, img_channel_index)
+
+        if self.horizontal_flip:
+            if np.random.random() < 0.5:
+                x = flip_axis(x, img_col_index)
+
+        if self.vertical_flip:
+            if np.random.random() < 0.5:
+                x = flip_axis(x, img_row_index)
+
         # TODO:
-        # zoom
+        # channel-wise normalization
         # barrel/fisheye
-        # shearing
-        # channel shifting
         return x
 
     def fit(self, X,
-            augment=False,  # fit on randomly augmented samples
-            rounds=1,  # if augment, how many augmentation passes over the data do we use
+            augment=False,
+            rounds=1,
             seed=None):
-        '''Required for featurewise_center, featurewise_std_normalization and zca_whitening.
+        '''Required for featurewise_center, featurewise_std_normalization
+        and zca_whitening.
+
+        # Arguments
+            X: Numpy array, the data to fit on.
+            augment: whether to fit on randomly augmented samples
+            rounds: if `augment`,
+                how many augmentation passes to do over the data
+            seed: random seed.
         '''
         X = np.copy(X)
         if augment:
-            aX = np.zeros(tuple([rounds*X.shape[0]]+list(X.shape)[1:]))
+            aX = np.zeros(tuple([rounds * X.shape[0]] + list(X.shape)[1:]))
             for r in range(rounds):
                 for i in range(X.shape[0]):
-                    img = array_to_img(X[i])
-                    img = self.random_transform(img)
-                    aX[i+r*X.shape[0]] = img_to_array(img)
+                    aX[i + r * X.shape[0]] = self.random_transform(X[i])
             X = aX
 
         if self.featurewise_center:
             self.mean = np.mean(X, axis=0)
             X -= self.mean
+
         if self.featurewise_std_normalization:
             self.std = np.std(X, axis=0)
-            X /= self.std
+            X /= (self.std + 1e-7)
 
         if self.zca_whitening:
-            flatX = np.reshape(X, (X.shape[0], X.shape[1]*X.shape[2]*X.shape[3]))
-            fudge = 10e-6
+            flatX = np.reshape(X, (X.shape[0], X.shape[1] * X.shape[2] * X.shape[3]))
             sigma = np.dot(flatX.T, flatX) / flatX.shape[1]
             U, S, V = linalg.svd(sigma)
-            self.principal_components = np.dot(np.dot(U, np.diag(1. / np.sqrt(S + fudge))), U.T)
+            self.principal_components = np.dot(np.dot(U, np.diag(1. / np.sqrt(S + 10e-7))), U.T)
 
 
 class GraphImageDataGenerator(ImageDataGenerator):
     '''Example of how to build a generator for a Graph model
     '''
-
     def next(self):
         bX, bY = super(GraphImageDataGenerator, self).next()
         return {'input': bX, 'output': bY}

keras/preprocessing/sequence.py

@@ -4,19 +4,20 @@ import numpy as np
 import random
 from six.moves import range
 
-def pad_sequences(sequences, maxlen=None, dtype='int32', padding='pre', truncating='pre', value=0.):
-    """
-        Pad each sequence to the same length:
-        the length of the longest sequence.
 
-        If maxlen is provided, any sequence longer
-        than maxlen is truncated to maxlen. Truncation happens off either the beginning (default) or
-        the end of the sequence.
+def pad_sequences(sequences, maxlen=None, dtype='int32',
+                  padding='pre', truncating='pre', value=0.):
+    '''Pads each sequence to the same length:
+    the length of the longest sequence.
 
-        Supports post-padding and pre-padding (default).
+    If maxlen is provided, any sequence longer
+    than maxlen is truncated to maxlen.
+    Truncation happens off either the beginning (default) or
+    the end of the sequence.
 
-        Parameters:
-        -----------
+    Supports post-padding and pre-padding (default).
+
+    # Arguments
         sequences: list of lists where each element is a sequence
         maxlen: int, maximum length
         dtype: type to cast the resulting sequence.
@@ -25,53 +26,64 @@ def pad_sequences(sequences, maxlen=None, dtype='int32', padding='pre', truncati
             maxlen either in the beginning or in the end of the sequence
         value: float, value to pad the sequences to the desired value.
 
-        Returns:
+    # Returns
         x: numpy array with dimensions (number_of_sequences, maxlen)
-
-    """
+    '''
     lengths = [len(s) for s in sequences]
 
     nb_samples = len(sequences)
     if maxlen is None:
         maxlen = np.max(lengths)
 
-    x = (np.ones((nb_samples, maxlen)) * value).astype(dtype)
+    # take the sample shape from the first non empty sequence
+    # checking for consistency in the main loop below.
+    sample_shape = tuple()
+    for s in sequences:
+        if len(s) > 0:
+            sample_shape = np.asarray(s).shape[1:]
+            break
+
+    x = (np.ones((nb_samples, maxlen) + sample_shape) * value).astype(dtype)
     for idx, s in enumerate(sequences):
         if len(s) == 0:
-            continue # empty list was found
+            continue  # empty list was found
         if truncating == 'pre':
             trunc = s[-maxlen:]
         elif truncating == 'post':
             trunc = s[:maxlen]
         else:
-            raise ValueError("Truncating type '%s' not understood" % padding)
+            raise ValueError('Truncating type "%s" not understood' % truncating)
+
+        # check `trunc` has expected shape
+        trunc = np.asarray(trunc, dtype=dtype)
+        if trunc.shape[1:] != sample_shape:
+            raise ValueError('Shape of sample %s of sequence at position %s is different from expected shape %s' %
+                             (trunc.shape[1:], idx, sample_shape))
 
         if padding == 'post':
             x[idx, :len(trunc)] = trunc
         elif padding == 'pre':
             x[idx, -len(trunc):] = trunc
         else:
-            raise ValueError("Padding type '%s' not understood" % padding)
+            raise ValueError('Padding type "%s" not understood' % padding)
     return x
 
 
 def make_sampling_table(size, sampling_factor=1e-5):
-    '''
-        This generates an array where the ith element
-        is the probability that a word of rank i would be sampled,
-        according to the sampling distribution used in word2vec.
+    '''This generates an array where the ith element
+    is the probability that a word of rank i would be sampled,
+    according to the sampling distribution used in word2vec.
 
-        The word2vec formula is:
-            p(word) = min(1, sqrt(word.frequency/sampling_factor) / (word.frequency/sampling_factor))
+    The word2vec formula is:
+        p(word) = min(1, sqrt(word.frequency/sampling_factor) / (word.frequency/sampling_factor))
 
-        We assume that the word frequencies follow Zipf's law (s=1) to derive
-        a numerical approximation of frequency(rank):
-           frequency(rank) ~ 1/(rank * (log(rank) + gamma) + 1/2 - 1/(12*rank))
+    We assume that the word frequencies follow Zipf's law (s=1) to derive
+    a numerical approximation of frequency(rank):
+       frequency(rank) ~ 1/(rank * (log(rank) + gamma) + 1/2 - 1/(12*rank))
         where gamma is the Euler-Mascheroni constant.
 
-        Parameters:
-        -----------
-        size: int, number of possible words to sample. 
+    # Arguments
+        size: int, number of possible words to sample.
     '''
     gamma = 0.577
     rank = np.array(list(range(size)))
@@ -85,28 +97,28 @@ def make_sampling_table(size, sampling_factor=1e-5):
 def skipgrams(sequence, vocabulary_size,
               window_size=4, negative_samples=1., shuffle=True,
               categorical=False, sampling_table=None):
-    '''
-        Take a sequence (list of indexes of words),
-        returns couples of [word_index, other_word index] and labels (1s or 0s),
-        where label = 1 if 'other_word' belongs to the context of 'word',
-        and label=0 if 'other_word' is ramdomly sampled
+    '''Take a sequence (list of indexes of words),
+    returns couples of [word_index, other_word index] and labels (1s or 0s),
+    where label = 1 if 'other_word' belongs to the context of 'word',
+    and label=0 if 'other_word' is ramdomly sampled
 
-        Paramaters:
-        -----------
+    # Arguments
         vocabulary_size: int. maximum possible word index + 1
-        window_size: int. actually half-window. The window of a word wi will be [i-window_size, i+window_size+1]
-        negative_samples: float >= 0. 0 for no negative (=random) samples. 1 for same number as positive samples. etc.
-        categorical: bool. if False, labels will be integers (eg. [0, 1, 1 .. ]),
+        window_size: int. actually half-window.
+            The window of a word wi will be [i-window_size, i+window_size+1]
+        negative_samples: float >= 0. 0 for no negative (=random) samples.
+            1 for same number as positive samples. etc.
+        categorical: bool. if False, labels will be
+            integers (eg. [0, 1, 1 .. ]),
             if True labels will be categorical eg. [[1,0],[0,1],[0,1] .. ]
 
-        Returns:
-        --------
+    # Returns
         couples, lables: where `couples` are int pairs and
             `labels` are either 0 or 1.
 
-        Notes:
-        ------
-        By convention, index 0 in the vocabulary is a non-word and will be skipped.
+    # Notes
+        By convention, index 0 in the vocabulary is
+        a non-word and will be skipped.
     '''
     couples = []
     labels = []

keras/preprocessing/text.py

@@ -1,7 +1,6 @@
 # -*- coding: utf-8 -*-
-'''
-    These preprocessing utils would greatly benefit
-    from a fast Cython rewrite.
+'''These preprocessing utilities would greatly benefit
+from a fast Cython rewrite.
 '''
 from __future__ import absolute_import
 
@@ -75,8 +74,7 @@ class Tokenizer(object):
         self.char_level = char_level
 
     def fit_on_texts(self, texts):
-        '''
-            required before using texts_to_sequences or texts_to_matrix
+        '''Required before using texts_to_sequences or texts_to_matrix
 
         # Arguments
             texts: can be a list of strings,
@@ -107,9 +105,8 @@ class Tokenizer(object):
             self.index_docs[self.word_index[w]] = c
 
     def fit_on_sequences(self, sequences):
-        '''
-            required before using sequences_to_matrix
-            (if fit_on_texts was never called)
+        '''Required before using sequences_to_matrix
+        (if fit_on_texts was never called)
         '''
         self.document_count = len(sequences)
         self.index_docs = {}
@@ -122,12 +119,11 @@ class Tokenizer(object):
                     self.index_docs[i] += 1
 
     def texts_to_sequences(self, texts):
-        '''
-            Transform each text in texts in a sequence of integers.
-            Only top "nb_words" most frequent words will be taken into account.
-            Only words known by the tokenizer will be taken into account.
+        '''Transforms each text in texts in a sequence of integers.
+        Only top "nb_words" most frequent words will be taken into account.
+        Only words known by the tokenizer will be taken into account.
 
-            Returns a list of sequences.
+        Returns a list of sequences.
         '''
         res = []
         for vect in self.texts_to_sequences_generator(texts):
@@ -135,12 +131,14 @@ class Tokenizer(object):
         return res
 
     def texts_to_sequences_generator(self, texts):
-        '''
-            Transform each text in texts in a sequence of integers.
-            Only top "nb_words" most frequent words will be taken into account.
-            Only words known by the tokenizer will be taken into account.
+        '''Transforms each text in texts in a sequence of integers.
+        Only top "nb_words" most frequent words will be taken into account.
+        Only words known by the tokenizer will be taken into account.
 
-            Yields individual sequences.
+        Yields individual sequences.
+
+        # Arguments:
+            texts: list of strings.
         '''
         nb_words = self.nb_words
         for text in texts:
@@ -150,56 +148,67 @@ class Tokenizer(object):
                 i = self.word_index.get(w)
                 if i is not None:
                     if nb_words and i >= nb_words:
-                        pass
+                        continue
                     else:
                         vect.append(i)
             yield vect
 
-    def texts_to_matrix(self, texts, mode="binary"):
-        '''
-            modes: binary, count, tfidf, freq
+    def texts_to_matrix(self, texts, mode='binary'):
+        '''Convert a list of texts to a Numpy matrix,
+        according to some vectorization mode.
+
+        # Arguments:
+            texts: list of strings.
+            modes: one of "binary", "count", "tfidf", "freq"
         '''
         sequences = self.texts_to_sequences(texts)
         return self.sequences_to_matrix(sequences, mode=mode)
 
-    def sequences_to_matrix(self, sequences, mode="binary"):
-        '''
-            modes: binary, count, tfidf, freq
+    def sequences_to_matrix(self, sequences, mode='binary'):
+        '''Converts a list of sequences into a Numpy matrix,
+        according to some vectorization mode.
+
+        # Arguments:
+            sequences: list of sequences
+                (a sequence is a list of integer word indices).
+            modes: one of "binary", "count", "tfidf", "freq"
         '''
         if not self.nb_words:
             if self.word_index:
                 nb_words = len(self.word_index) + 1
             else:
-                raise Exception("Specify a dimension (nb_words argument), or fit on some text data first.")
+                raise Exception('Specify a dimension (nb_words argument), '
+                                'or fit on some text data first.')
         else:
             nb_words = self.nb_words
 
-        if mode == "tfidf" and not self.document_count:
-            raise Exception("Fit the Tokenizer on some data before using tfidf mode.")
+        if mode == 'tfidf' and not self.document_count:
+            raise Exception('Fit the Tokenizer on some data '
+                            'before using tfidf mode.')
 
         X = np.zeros((len(sequences), nb_words))
         for i, seq in enumerate(sequences):
             if not seq:
-                pass
+                continue
             counts = {}
             for j in seq:
                 if j >= nb_words:
-                    pass
+                    continue
                 if j not in counts:
                     counts[j] = 1.
                 else:
                     counts[j] += 1
             for j, c in list(counts.items()):
-                if mode == "count":
+                if mode == 'count':
                     X[i][j] = c
-                elif mode == "freq":
+                elif mode == 'freq':
                     X[i][j] = c / len(seq)
-                elif mode == "binary":
+                elif mode == 'binary':
                     X[i][j] = 1
-                elif mode == "tfidf":
+                elif mode == 'tfidf':
                     tf = np.log(c / len(seq))
                     df = (1 + np.log(1 + self.index_docs.get(j, 0) / (1 + self.document_count)))
                     X[i][j] = tf / df
                 else:
-                    raise Exception("Unknown vectorization mode: " + str(mode))
+                    raise Exception('Unknown vectorization mode: ' + str(mode))
         return X

keras/regularizers.py

@@ -13,46 +13,63 @@ class Regularizer(object):
         return loss
 
     def get_config(self):
-        return {"name": self.__class__.__name__}
+        return {'name': self.__class__.__name__}
 
 
 class WeightRegularizer(Regularizer):
     def __init__(self, l1=0., l2=0.):
-        self.l1 = l1
-        self.l2 = l2
+        self.l1 = K.cast_to_floatx(l1)
+        self.l2 = K.cast_to_floatx(l2)
+        self.uses_learning_phase = True
 
     def set_param(self, p):
         self.p = p
 
     def __call__(self, loss):
-        loss += K.sum(K.abs(self.p)) * self.l1
-        loss += K.sum(K.square(self.p)) * self.l2
-        return loss
+        if not hasattr(self, 'p'):
+            raise Exception('Need to call `set_param` on '
+                            'WeightRegularizer instance '
+                            'before calling the instance. '
+                            'Check that you are not passing '
+                            'a WeightRegularizer instead of an '
+                            'ActivityRegularizer '
+                            '(i.e. activity_regularizer="l2" instead '
+                            'of activity_regularizer="activity_l2".')
+        regularized_loss = loss + K.sum(K.abs(self.p)) * self.l1
+        regularized_loss += K.sum(K.square(self.p)) * self.l2
+        return K.in_train_phase(regularized_loss, loss)
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "l1": self.l1,
-                "l2": self.l2}
+        return {'name': self.__class__.__name__,
+                'l1': self.l1,
+                'l2': self.l2}
 
 
 class ActivityRegularizer(Regularizer):
     def __init__(self, l1=0., l2=0.):
-        self.l1 = l1
-        self.l2 = l2
+        self.l1 = K.cast_to_floatx(l1)
+        self.l2 = K.cast_to_floatx(l2)
+        self.uses_learning_phase = True
 
     def set_layer(self, layer):
         self.layer = layer
 
     def __call__(self, loss):
-        output = self.layer.get_output(True)
-        loss += self.l1 * K.sum(K.mean(K.abs(output), axis=0))
-        loss += self.l2 * K.sum(K.mean(K.square(output), axis=0))
-        return loss
+        if not hasattr(self, 'layer'):
+            raise Exception('Need to call `set_layer` on '
+                            'ActivityRegularizer instance '
+                            'before calling the instance.')
+        regularized_loss = loss
+        for i in range(len(self.layer.inbound_nodes)):
+            output = self.layer.get_output_at(i)
+            regularized_loss += self.l1 * K.sum(K.mean(K.abs(output), axis=0))
+            regularized_loss += self.l2 * K.sum(K.mean(K.square(output), axis=0))
+        return K.in_train_phase(regularized_loss, loss)
 
     def get_config(self):
-        return {"name": self.__class__.__name__,
-                "l1": self.l1,
-                "l2": self.l2}
+        return {'name': self.__class__.__name__,
+                'l1': self.l1,
+                'l2': self.l2}
 
 
 def l1(l=0.01):
@@ -78,7 +95,6 @@ def activity_l2(l=0.01):
 def activity_l1l2(l1=0.01, l2=0.01):
     return ActivityRegularizer(l1=l1, l2=l2)
 
-identity = Regularizer
 
 from .utils.generic_utils import get_from_module
 def get(identifier, kwargs=None):

keras/utils/data_utils.py

@@ -0,0 +1,95 @@
+from __future__ import absolute_import
+from __future__ import print_function
+
+import tarfile
+import os
+import sys
+import shutil
+from six.moves.urllib.request import urlopen
+from six.moves.urllib.error import URLError, HTTPError
+
+from ..utils.generic_utils import Progbar
+
+
+# Under Python 2, 'urlretrieve' relies on FancyURLopener from legacy
+# urllib module, known to have issues with proxy management
+if sys.version_info[0] == 2:
+    def urlretrieve(url, filename, reporthook=None, data=None):
+        def chunk_read(response, chunk_size=8192, reporthook=None):
+            total_size = response.info().get('Content-Length').strip()
+            total_size = int(total_size)
+            count = 0
+            while 1:
+                chunk = response.read(chunk_size)
+                if not chunk:
+                    break
+                count += 1
+                if reporthook:
+                    reporthook(count, chunk_size, total_size)
+                yield chunk
+
+        response = urlopen(url, data)
+        with open(filename, 'wb') as fd:
+            for chunk in chunk_read(response, reporthook=reporthook):
+                fd.write(chunk)
+else:
+    from six.moves.urllib.request import urlretrieve
+
+
+def get_file(fname, origin, untar=False):
+    datadir_base = os.path.expanduser(os.path.join('~', '.keras'))
+    if not os.access(datadir_base, os.W_OK):
+        datadir_base = os.path.join('/tmp', '.keras')
+    datadir = os.path.join(datadir_base, 'datasets')
+    if not os.path.exists(datadir):
+        os.makedirs(datadir)
+
+    if untar:
+        untar_fpath = os.path.join(datadir, fname)
+        fpath = untar_fpath + '.tar.gz'
+    else:
+        fpath = os.path.join(datadir, fname)
+
+    if not os.path.exists(fpath):
+        print('Downloading data from',  origin)
+        global progbar
+        progbar = None
+
+        def dl_progress(count, block_size, total_size):
+            global progbar
+            if progbar is None:
+                progbar = Progbar(total_size)
+            else:
+                progbar.update(count*block_size)
+
+        error_msg = 'URL fetch failure on {}: {} -- {}'
+        try:
+            try:
+                urlretrieve(origin, fpath, dl_progress)
+            except URLError as e:
+                raise Exception(error_msg.format(origin, e.errno, e.reason))
+            except HTTPError as e:
+                raise Exception(error_msg.format(origin, e.code, e.msg))
+        except (Exception, KeyboardInterrupt) as e:
+            if os.path.exists(fpath):
+                os.remove(fpath)
+            raise
+        progbar = None
+
+    if untar:
+        if not os.path.exists(untar_fpath):
+            print('Untaring file...')
+            tfile = tarfile.open(fpath, 'r:gz')
+            try:
+                tfile.extractall(path=datadir)
+            except (Exception, KeyboardInterrupt) as e:
+                if os.path.exists(untar_fpath):
+                    if os.path.isfile(untar_fpath):
+                        os.remove(untar_fpath)
+                    else:
+                        shutil.rmtree(untar_fpath)
+                raise
+            tfile.close()
+        return untar_fpath
+
+    return fpath

keras/utils/generic_utils.py

@@ -18,6 +18,14 @@ def get_from_module(identifier, module_params, module_name,
             return res(**kwargs)
         else:
             return res
+    elif type(identifier) is dict:
+        name = identifier.pop('name')
+        res = module_params.get(name)
+        if res:
+            return res(**identifier)
+        else:
+            raise Exception('Invalid ' + str(module_name) + ': ' +
+                            str(identifier))
     return identifier
 
 
@@ -63,15 +71,15 @@ class Progbar(object):
             numdigits = int(np.floor(np.log10(self.target))) + 1
             barstr = '%%%dd/%%%dd [' % (numdigits, numdigits)
             bar = barstr % (current, self.target)
-            prog = float(current)/self.target
-            prog_width = int(self.width*prog)
+            prog = float(current) / self.target
+            prog_width = int(self.width * prog)
             if prog_width > 0:
-                bar += ('='*(prog_width-1))
+                bar += ('=' * (prog_width-1))
                 if current < self.target:
                     bar += '>'
                 else:
                     bar += '='
-            bar += ('.'*(self.width-prog_width))
+            bar += ('.' * (self.width - prog_width))
             bar += ']'
             sys.stdout.write(bar)
             self.total_width = len(bar)
@@ -80,7 +88,7 @@ class Progbar(object):
                 time_per_unit = (now - self.start) / current
             else:
                 time_per_unit = 0
-            eta = time_per_unit*(self.target - current)
+            eta = time_per_unit * (self.target - current)
             info = ''
             if current < self.target:
                 info += ' - ETA: %ds' % eta
@@ -99,7 +107,7 @@ class Progbar(object):
 
             self.total_width += len(info)
             if prev_total_width > self.total_width:
-                info += ((prev_total_width-self.total_width) * " ")
+                info += ((prev_total_width - self.total_width) * " ")
 
             sys.stdout.write(info)
             sys.stdout.flush()
@@ -120,4 +128,18 @@ class Progbar(object):
                 sys.stdout.write(info + "\n")
 
     def add(self, n, values=[]):
-        self.update(self.seen_so_far+n, values)
+        self.update(self.seen_so_far + n, values)
+
+
+def display_table(rows, positions):
+
+    def display_row(objects, positions):
+        line = ''
+        for i in range(len(objects)):
+            line += str(objects[i])
+            line = line[:positions[i]]
+            line += ' ' * (positions[i] - len(line))
+        print(line)
+
+    for objects in rows:
+        display_row(objects, positions)

keras/utils/layer_utils.py

@@ -1,158 +1,97 @@
 from __future__ import print_function
-import inspect
-import numpy as np
-import copy
 
-from ..layers.advanced_activations import *
-from ..layers.core import *
-from ..layers.convolutional import *
-from ..layers.embeddings import *
-from ..layers.noise import *
-from ..layers.normalization import *
-from ..layers.recurrent import *
-from ..layers import containers
-from .. import regularizers
-from .. import constraints
+from .generic_utils import get_from_module
+from ..layers import *
+from ..models import Model, Sequential, Graph
+from .. import backend as K
 
 
-def container_from_config(original_layer_dict, custom_objects={}):
-    layer_dict = copy.deepcopy(original_layer_dict)
-    name = layer_dict.get('name')
+def layer_from_config(config, custom_objects={}):
+    '''
+    # Arguments
+        config: dict of the form {'class_name': str, 'config': dict}
+        custom_objects: dict mapping class names (or function names)
+            of custom (non-Keras) objects to class/functions
 
+    # Returns
+        Layer instance (may be Model, Sequential, Graph, Layer...)
+    '''
     # Insert custom layers into globals so they can
     # be accessed by `get_from_module`.
     for cls_key in custom_objects:
         globals()[cls_key] = custom_objects[cls_key]
 
-    if name == 'Merge':
-        mode = layer_dict.get('mode')
-        concat_axis = layer_dict.get('concat_axis')
-        dot_axes = layer_dict.get('dot_axes')
-        layers = layer_dict.get('layers')
-        layer_list = []
-        for layer in layers:
-            init_layer = container_from_config(layer)
-            layer_list.append(init_layer)
-        merge_layer = Merge(layer_list, mode, concat_axis, dot_axes)
-        return merge_layer
+    class_name = config['class_name']
 
-    elif name == 'Sequential':
-        layers = layer_dict.get('layers')
-        layer_list = []
-        for layer in layers:
-            init_layer = container_from_config(layer)
-            layer_list.append(init_layer)
-        seq_layer = containers.Sequential(layer_list)
-        return seq_layer
-
-    elif name == 'Graph':
-        graph_layer = containers.Graph()
-        inputs = layer_dict.get('input_config')
-
-        for input in inputs:
-            graph_layer.add_input(**input)
-
-        nodes = layer_dict.get('node_config')
-        for node in nodes:
-            layer = container_from_config(layer_dict['nodes'].get(node['name']))
-            node['layer'] = layer
-            graph_layer.add_node(**node)
-
-        outputs = layer_dict.get('output_config')
-        for output in outputs:
-            graph_layer.add_output(**output)
-        return graph_layer
-
-    elif name == 'AutoEncoder':
-        kwargs = {'encoder': container_from_config(layer_dict.get('encoder_config')),
-                  'decoder': container_from_config(layer_dict.get('decoder_config'))}
-        for kwarg in ['output_reconstruction', 'weights']:
-            if kwarg in layer_dict:
-                kwargs[kwarg] = layer_dict[kwarg]
-        return AutoEncoder(**kwargs)
-
-    else:  # this is a non-topological layer (e.g. Dense, etc.)
-        layer_dict.pop('name')
-
-        for k, v in layer_dict.items():
-            # a dictionary argument may be a regularizer or constraint
-            if isinstance(v, dict):
-                vname = v.pop('name')
-                if vname in [x for x, y in inspect.getmembers(constraints, predicate=inspect.isclass)]:
-                    layer_dict[k] = constraints.get(vname, v)
-                elif vname in [x for x, y in inspect.getmembers(regularizers, predicate=inspect.isclass)]:
-                    layer_dict[k] = regularizers.get(vname, v)
-                else:
-                    # not a regularizer of constraint, don't touch it
-                    v['name'] = vname
-
-        # the "name" keyword argument of layers is saved as "custom_name"
-        if 'custom_name' in layer_dict:
-            layer_dict['name'] = layer_dict.pop('custom_name')
-        base_layer = get_layer(name, layer_dict)
-        return base_layer
+    if class_name == 'Sequential':
+        layer_class = Sequential
+    elif class_name == 'Graph':
+        layer_class = Graph
+    elif class_name in ['Model', 'Container']:
+        layer_class = Model
+    else:
+        layer_class = get_from_module(class_name, globals(), 'layer',
+                                      instantiate=False)
+    return layer_class.from_config(config['config'])
 
 
-def model_summary(model):
-    param_count = 0  # param count in the model
+def print_summary(layers, relevant_nodes=None):
+    line_length = 100  # total length of printed lines
+    positions = [35, 55, 67, 100]  # absolute positions of log elements in each line
+    # header names for the different log elements
+    to_display = ['Layer (type)', 'Output Shape', 'Param #', 'Connected to']
 
-    def display(objects, positions):
+    def print_row(fields, positions):
         line = ''
-        for i in range(len(objects)):
-            line += str(objects[i])
+        for i in range(len(fields)):
+            line += str(fields[i])
             line = line[:positions[i]]
             line += ' ' * (positions[i] - len(line))
         print(line)
 
-    def display_layer_info(layer, name, positions):
-        layer_type = layer.__class__.__name__
-        output_shape = layer.output_shape
-        params = layer.count_params()
-        to_display = ['%s (%s)' % (layer_type, name), output_shape, params]
-        display(to_display, positions)
+    print('_' * line_length)
+    print_row(to_display, positions)
+    print('=' * line_length)
 
-    line_length = 80  # total length of printed lines
-    positions = [30, 60, 80]  # absolute positions of log elements in each line
-    # header names for the different log elements
-    to_display = ['Layer (name)', 'Output Shape', 'Param #']
+    def print_layer_summary(layer):
+        try:
+            output_shape = layer.output_shape
+        except:
+            output_shape = 'multiple'
+        connections = []
+        for node_index, node in enumerate(layer.inbound_nodes):
+            if relevant_nodes:
+                node_key = layer.name + '_ib-' + str(node_index)
+                if node_key not in relevant_nodes:
+                    # node is node part of the current network
+                    continue
+            for i in range(len(node.inbound_layers)):
+                inbound_layer = node.inbound_layers[i].name
+                inbound_node_index = node.node_indices[i]
+                inbound_tensor_index = node.tensor_indices[i]
+                connections.append(inbound_layer + '[' + str(inbound_node_index) + '][' + str(inbound_tensor_index) + ']')
 
-    # for sequential models, we start by printing
-    # the expect input shape
-    if model.__class__.__name__ == 'Sequential':
-        print('-' * line_length)
-        print('Initial input shape: ' + str(model.input_shape))
+        name = layer.name
+        cls_name = layer.__class__.__name__
+        if not connections:
+            first_connection = ''
+        else:
+            first_connection = connections[0]
+        fields = [name + ' (' + cls_name + ')', output_shape, layer.count_params(), first_connection]
+        print_row(fields, positions)
+        if len(connections) > 1:
+            for i in range(1, len(connections)):
+                fields = ['', '', '', connections[i]]
+                print_row(fields, positions)
 
-    # print header
-    print('-' * line_length)
-    display(to_display, positions)
-    print('-' * line_length)
+    total_params = 0
+    for i in range(len(layers)):
+        print_layer_summary(layers[i])
+        if i == len(layers) - 1:
+            print('=' * line_length)
+        else:
+            print('_' * line_length)
+        total_params += layers[i].count_params()
 
-    if model.__class__.__name__ == 'Sequential':
-        for layer in model.layers:
-            name = getattr(layer, 'name', 'Unnamed')
-            display_layer_info(layer, name, positions)
-            param_count += layer.count_params()
-
-    elif model.__class__.__name__ == 'Graph':
-        for name in model.input_order:
-            layer = model.inputs[name]
-            display_layer_info(layer, name, positions)
-
-        for name in model.nodes:
-            layer = model.nodes[name]
-            display_layer_info(layer, name, positions)
-            param_count += layer.count_params()
-
-        for name in model.output_order:
-            layer = model.outputs[name]
-            display_layer_info(layer, name, positions)
-
-    print('-' * line_length)
-    print('Total params: %s' % param_count)
-    print('-' * line_length)
-
-
-from .generic_utils import get_from_module
-def get_layer(identifier, kwargs=None):
-    return get_from_module(identifier, globals(), 'layer',
-                           instantiate=True, kwargs=kwargs)
+    print('Total params: %s' % total_params)
+    print('_' * line_length)

keras/utils/np_utils.py

@@ -9,7 +9,6 @@ def to_categorical(y, nb_classes=None):
     '''Convert class vector (integers from 0 to nb_classes)
     to binary class matrix, for use with categorical_crossentropy.
     '''
-    y = np.asarray(y, dtype='int32')
     if not nb_classes:
         nb_classes = np.max(y)+1
     Y = np.zeros((len(y), nb_classes))
@@ -51,3 +50,27 @@ def probas_to_classes(y_pred):
 
 def categorical_probas_to_classes(p):
     return np.argmax(p, axis=1)
+
+
+def convert_kernel(kernel, dim_ordering='th'):
+    '''Converts a kernel matrix (numpy array)
+    from Theano format to TensorFlow format
+    (or reciprocally, since the transformation
+    is its own inverse).
+    '''
+    new_kernel = np.copy(kernel)
+    if dim_ordering == 'th':
+        w = kernel.shape[2]
+        h = kernel.shape[3]
+        for i in range(w):
+            for j in range(h):
+                new_kernel[:, :, i, j] = kernel[:, :, w - i - 1, h - j - 1]
+    elif dim_ordering == 'tf':
+        w = kernel.shape[0]
+        h = kernel.shape[1]
+        for i in range(w):
+            for j in range(h):
+                new_kernel[i, j, :, :] = kernel[w - i - 1, h - j - 1, :, :]
+    else:
+        raise Exception('Invalid dim_ordering: ' + str(dim_ordering))
+    return new_kernel

keras/utils/test_utils.py

@@ -1,7 +1,14 @@
 import numpy as np
+from numpy.testing import assert_allclose
+import inspect
+
+from ..engine import Model, Input
+from ..models import Sequential, model_from_json
+from .. import backend as K
 
 
-def get_test_data(nb_train=1000, nb_test=500, input_shape=(10,), output_shape=(2,),
+def get_test_data(nb_train=1000, nb_test=500, input_shape=(10,),
+                  output_shape=(2,),
                   classification=True, nb_class=2):
     '''
         classification=True overrides output_shape
@@ -25,3 +32,73 @@ def get_test_data(nb_train=1000, nb_test=500, input_shape=(10,), output_shape=(2
             y[i] = np.random.normal(loc=y_loc[i], scale=0.7, size=output_shape)
 
     return (X[:nb_train], y[:nb_train]), (X[nb_train:], y[nb_train:])
+
+
+def layer_test(layer_cls, kwargs={}, input_shape=None, input_dtype=None,
+               input_data=None, expected_output=None, expected_output_dtype=None):
+    '''Test routine for a layer with a single input tensor
+    and single output tensor.
+    '''
+    if input_data is None:
+        assert input_shape
+        if not input_dtype:
+            input_dtype = K.floatx()
+        input_data = (10 * np.random.random(input_shape)).astype(input_dtype)
+    elif input_shape is None:
+        input_shape = input_data.shape
+
+    if expected_output_dtype is None:
+        expected_output_dtype = input_dtype
+
+    # instantiation
+    layer = layer_cls(**kwargs)
+
+    # test get_weights , set_weights
+    weights = layer.get_weights()
+    layer.set_weights(weights)
+
+    # test and instantiation from weights
+    if 'weights' in inspect.getargspec(layer_cls.__init__):
+        kwargs['weights'] = weights
+        layer = layer_cls(**kwargs)
+
+    # test in functional API
+    x = Input(shape=input_shape[1:], dtype=input_dtype)
+    y = layer(x)
+    assert K.dtype(y) == expected_output_dtype
+
+    model = Model(input=x, output=y)
+    model.compile('rmsprop', 'mse')
+
+    expected_output_shape = layer.get_output_shape_for(input_shape)
+    actual_output = model.predict(input_data)
+    actual_output_shape = actual_output.shape
+    assert expected_output_shape == actual_output_shape
+    if expected_output is not None:
+        assert_allclose(actual_output, expected_output, rtol=1e-3)
+
+    # test serialization
+    model_config = model.get_config()
+    model = Model.from_config(model_config)
+    model.compile('rmsprop', 'mse')
+
+    # test as first layer in Sequential API
+    layer_config = layer.get_config()
+    layer_config['batch_input_shape'] = input_shape
+    layer = layer.__class__.from_config(layer_config)
+
+    model = Sequential()
+    model.add(layer)
+    model.compile('rmsprop', 'mse')
+    actual_output = model.predict(input_data)
+    actual_output_shape = actual_output.shape
+    assert expected_output_shape == actual_output_shape
+    if expected_output is not None:
+        assert_allclose(actual_output, expected_output, rtol=1e-3)
+
+    # test JSON serialization
+    json_model = model.to_json()
+    model = model_from_json(json_model)
+
+    # for further checks in the caller function
+    return actual_output

keras/utils/visualize_util.py

@@ -1,7 +1,3 @@
-import itertools
-from keras.layers.containers import Graph, Sequential
-from keras.layers.core import Merge
-
 try:
     # pydot-ng is a fork of pydot that is better maintained
     import pydot_ng as pydot
@@ -9,146 +5,60 @@ except ImportError:
     # fall back on pydot if necessary
     import pydot
 if not pydot.find_graphviz():
-    raise RuntimeError("Failed to import pydot. You must install pydot"
-                       " and graphviz for `pydotprint` to work.")
+    raise RuntimeError('Failed to import pydot. You must install pydot'
+                       ' and graphviz for `pydotprint` to work.')
 
 
-def layer_typename(layer):
-    return type(layer).__module__ + "." + type(layer).__name__
+def model_to_dot(model, show_shapes=False):
+    dot = pydot.Dot()
+    dot.set('rankdir', 'TB')
+    dot.set('concentrate', True)
+    dot.set_node_defaults(shape='record')
 
+    if model.__class__.__name__ == 'Sequential':
+        if not model.built:
+            model.build()
+        model = model.model
+    layers = model.layers
 
-def get_layer_to_name(model):
-    """Returns a dict mapping layer to their name in the model"""
-    if not isinstance(model, Graph):
-        return {}
-    else:
-        node_to_name = itertools.chain(
-            model.nodes.items(), model.inputs.items(), model.outputs.items()
-        )
-        return {v: k for k, v in node_to_name}
+    # first, populate the nodes of the graph
+    for layer in layers:
+        layer_id = str(id(layer))
+        label = str(layer.name) + ' (' + layer.__class__.__name__ + ')'
 
-
-class ModelToDot(object):
-    """
-    This is a helper class which visits a keras model (Sequential or Graph) and
-    returns a pydot.Graph representation.
-
-    This is implemented as a class because we need to maintain various states.
-
-    Use it as ```ModelToDot()(model)```
-
-    Keras models can have an arbitrary number of inputs and outputs. A given
-    layer can have multiple inputs but has a single output. We therefore
-    explore the model by starting at its output and crawling "up" the tree.
-    """
-    def _pydot_node_for_layer(self, layer, label):
-        """
-        Returns the pydot.Node corresponding to the given layer.
-        `label` specify the name of the layer (only used if the layer isn't yet
-            associated with a pydot.Node)
-        """
-        # Check if this already exists (will be the case for nodes that
-        # serve as input to more than one layer)
-        if layer in self.layer_to_pydotnode:
-            node = self.layer_to_pydotnode[layer]
-        else:
-            layer_id = 'layer%d' % self.idgen
-            self.idgen += 1
-
-            label = label + " (" + layer_typename(layer) + ")"
-
-            if self.show_shape:
-                # Build the label that will actually contain a table with the
-                # input/output
+        if show_shapes:
+            # Build the label that will actually contain a table with the
+            # input/output
+            try:
                 outputlabels = str(layer.output_shape)
-                if hasattr(layer, 'input_shape'):
-                    inputlabels = str(layer.input_shape)
-                elif hasattr(layer, 'input_shapes'):
-                    inputlabels = ', '.join(
-                        [str(ishape) for ishape in layer.input_shapes])
-                else:
-                    inputlabels = ''
-                label = "%s\n|{input:|output:}|{{%s}|{%s}}" % (
-                        label, inputlabels, outputlabels)
-
-            node = pydot.Node(layer_id, label=label)
-            self.g.add_node(node)
-            self.layer_to_pydotnode[layer] = node
-        return node
-
-    def _process_layer(self, layer, layer_to_name=None, connect_to=None):
-        """
-        Process a layer, adding its node to the graph and creating edges to its
-        outputs.
-
-        `connect_to` specify where the output of the current layer will be
-            connected
-        `layer_to_name` is a dict mapping layer to their name in the Graph
-            model. Should be {} when processing a Sequential model
-        """
-        # The layer can be a container layer, in which case we can recurse
-        is_graph = isinstance(layer, Graph)
-        is_seq = isinstance(layer, Sequential)
-        if self.recursive and (is_graph or is_seq):
-            # We got a container layer, recursively transform it
-            if is_graph:
-                child_layers = layer.outputs.values()
+            except:
+                outputlabels = 'multiple'
+            if hasattr(layer, 'input_shape'):
+                inputlabels = str(layer.input_shape)
+            elif hasattr(layer, 'input_shapes'):
+                inputlabels = ', '.join(
+                    [str(ishape) for ishape in layer.input_shapes])
             else:
-                child_layers = [layer.layers[-1]]
-            for l in child_layers:
-                self._process_layer(l, layer_to_name=get_layer_to_name(layer),
-                                    connect_to=connect_to)
-        else:
-            # This is a simple layer.
-            label = layer_to_name.get(layer, '')
-            layer_node = self._pydot_node_for_layer(layer, label=label)
+                inputlabels = 'multiple'
+            label = '%s\n|{input:|output:}|{{%s}|{%s}}' % (label, inputlabels, outputlabels)
 
-            if connect_to is not None:
-                self.g.add_edge(pydot.Edge(layer_node, connect_to))
+        node = pydot.Node(layer_id, label=label)
+        dot.add_node(node)
 
-            # Proceed upwards to the parent(s). Only Merge layers have more
-            # than one parent
-            if isinstance(layer, Merge):  # Merge layer
-                for l in layer.layers:
-                    self._process_layer(l, layer_to_name,
-                                        connect_to=layer_node)
-            elif hasattr(layer, 'previous') and layer.previous is not None:
-                self._process_layer(layer.previous, layer_to_name,
-                                    connect_to=layer_node)
-
-    def __call__(self, model, recursive=True, show_shape=False,
-                 connect_to=None):
-        self.idgen = 0
-        # Maps keras layer to the pydot.Node representing them
-        self.layer_to_pydotnode = {}
-        self.recursive = recursive
-        self.show_shape = show_shape
-
-        self.g = pydot.Dot()
-        self.g.set('rankdir', 'TB')
-        self.g.set('concentrate', True)
-        self.g.set_node_defaults(shape='record')
-
-        if hasattr(model, 'outputs'):
-            # Graph
-            for name, l in model.outputs.items():
-                self._process_layer(l, get_layer_to_name(model),
-                                    connect_to=connect_to)
-        else:
-            # Sequential container
-            self._process_layer(model.layers[-1], {}, connect_to=connect_to)
-
-        return self.g
+    # second, add the edges
+    for layer in layers:
+        layer_id = str(id(layer))
+        for i, node in enumerate(layer.inbound_nodes):
+            node_key = layer.name + '_ib-' + str(i)
+            if node_key in model.container_nodes:
+                # add edges
+                for inbound_layer in node.inbound_layers:
+                    inbound_layer_id = str(id(inbound_layer))
+                    layer_id = str(id(layer))
+                    dot.add_edge(pydot.Edge(inbound_layer_id, layer_id))
+    return dot
 
 
-def to_graph(model, **kwargs):
-    """
-    `recursive` controls whether we recursively explore container layers
-    `show_shape` controls whether the shape is shown in the graph
-    """
-    return ModelToDot()(model, **kwargs)
-
-
-def plot(model, to_file='model.png'):
-    graph = to_graph(model)
-    graph.write_png(to_file)
+def plot(model, to_file='model.png', show_shapes=False):
+    dot = model_to_dot(model, show_shapes)
+    dot.write_png(to_file)

keras/wrappers/scikit_learn.py

@@ -1,266 +1,277 @@
 from __future__ import absolute_import
-import abc
 import copy
-import numpy as np
+import inspect
+import types
 
 from ..utils.np_utils import to_categorical
+from ..models import Sequential
 
 
 class BaseWrapper(object):
-    """
-    Base class for the Keras scikit-learn wrapper.
+    '''Base class for the Keras scikit-learn wrapper.
 
-    Warning: This class should not be used directly. Use derived classes instead.
+    Warning: This class should not be used directly.
+    Use descendant classes instead.
 
-    Parameters
-    ----------
-    train_batch_size : int, optional
-        Number of training samples evaluated at a time.
-    test_batch_size : int, optional
-        Number of test samples evaluated at a time.
-    nb_epochs : int, optional
-        Number of training epochs.
-    shuffle : boolean, optional
-        Whether to shuffle the samples at each epoch.
-    show_accuracy : boolean, optional
-        Whether to display class accuracy in the logs at each epoch.
-    validation_split : float [0, 1], optional
-        Fraction of the data to use as held-out validation data.
-    validation_data : tuple (X, y), optional
-        Data to be used as held-out validation data. Will override validation_split.
-    callbacks : list, optional
-        List of callbacks to apply during training.
-    verbose : int, optional
-        Verbosity level.
-    """
-    __metaclass__ = abc.ABCMeta
+    # Arguments
+        build_fn: callable function or class instance
+        sk_params: model parameters & fitting parameters
 
-    @abc.abstractmethod
-    def __init__(self, model, optimizer, loss,
-                 train_batch_size=128, test_batch_size=128,
-                 nb_epoch=100, shuffle=True, show_accuracy=False,
-                 validation_split=0, validation_data=None, callbacks=None,
-                 verbose=0,):
-        self.model = model
-        self.optimizer = optimizer
-        self.loss = loss
-        self.compiled_model_ = None
-        self.classes_ = []
-        self.config_ = []
-        self.weights_ = []
+    The build_fn should construct, compile and return a Keras model, which
+    will then be used to fit/predict. One of the following
+    three values could be passed to build_fn:
+    1. A function
+    2. An instance of a class that implements the __call__ method
+    3. None. This means you implement a class that inherits from either
+    `KerasClassifier` or `KerasRegressor`. The __call__ method of the
+    present class will then be treated as the default build_fn.
 
-        self.train_batch_size = train_batch_size
-        self.test_batch_size = test_batch_size
-        self.nb_epoch = nb_epoch
-        self.shuffle = shuffle
-        self.show_accuracy = show_accuracy
-        self.validation_split = validation_split
-        self.validation_data = validation_data
-        self.callbacks = [] if callbacks is None else callbacks
+    `sk_params` takes both model parameters and fitting parameters. Legal model
+    parameters are the arguments of `build_fn`. Note that like all other
+    estimators in scikit-learn, 'build_fn' should provide defalult values for
+    its arguments, so that you could create the estimator without passing any
+    values to `sk_params`.
 
-        self.verbose = verbose
+    `sk_params` could also accept parameters for calling `fit`, `predict`,
+    `predict_proba`, and `score` methods (e.g., `nb_epoch`, `batch_size`).
+    fitting (predicting) parameters are selected in the following order:
+
+    1. Values passed to the dictionary arguments of
+    `fit`, `predict`, `predict_proba`, and `score` methods
+    2. Values passed to `sk_params`
+    3. The default values of the `keras.models.Sequential`
+    `fit`, `predict`, `predict_proba` and `score` methods
+
+    When using scikit-learn's `grid_search` API, legal tunable parameters are
+    those you could pass to `sk_params`, including fitting parameters.
+    In other words, you could use `grid_search` to search for the best
+    `batch_size` or `nb_epoch` as well as the model parameters.
+    '''
+
+    def __init__(self, build_fn=None, **sk_params):
+        self.build_fn = build_fn
+        self.sk_params = sk_params
+        self.check_params(sk_params)
+
+    def check_params(self, params):
+        '''Check for user typos in "params" keys to avoid
+        unwanted usage of default values
+
+        # Arguments
+            params: dictionary
+                The parameters to be checked
+        '''
+        legal_params_fns = [Sequential.fit, Sequential.predict,
+                            Sequential.predict_classes, Sequential.evaluate]
+        if self.build_fn is None:
+            legal_params_fns.append(self.__call__)
+        elif not isinstance(self.build_fn, types.FunctionType):
+            legal_params_fns.append(self.build_fn.__call__)
+        else:
+            legal_params_fns.append(self.build_fn)
+
+        legal_params = []
+        for fn in legal_params_fns:
+            legal_params += inspect.getargspec(fn)[0]
+        legal_params = set(legal_params)
+
+        for params_name in params:
+            if params_name not in legal_params:
+                assert False, '{} is not a legal parameter'.format(params_name)
 
     def get_params(self, deep=True):
-        """
-        Get parameters for this estimator.
+        '''Get parameters for this estimator.
 
-        Parameters
-        ----------
-        deep: boolean, optional
-            If True, will return the parameters for this estimator and
-            contained subobjects that are estimators.
+        # Arguments
+            deep: boolean, optional
+                If True, will return the parameters for this estimator and
+                contained sub-objects that are estimators.
 
-        Returns
-        -------
-        params : dict
-            Dictionary of parameter names mapped to their values.
-        """
-        return {'model': self.model, 'optimizer': self.optimizer, 'loss': self.loss}
+        # Returns
+            params : dict
+                Dictionary of parameter names mapped to their values.
+        '''
+        res = copy.deepcopy(self.sk_params)
+        res.update({'build_fn': self.build_fn})
+        return res
 
     def set_params(self, **params):
-        """
-        Set the parameters of this estimator.
+        '''Set the parameters of this estimator.
 
-        Parameters
-        ----------
+        # Arguments
         params: dict
             Dictionary of parameter names mapped to their values.
 
-        Returns
-        -------
-        self
-        """
-        for parameter, value in params.items():
-            setattr(self, parameter, value)
+        # Returns
+            self
+        '''
+        self.check_params(params)
+        self.sk_params.update(params)
         return self
 
-    def fit(self, X, y):
-        """
-        Fit the model according to the given training data.
+    def fit(self, X, y, **kwargs):
+        '''Construct a new model with build_fn and fit the model according
+        to the given training data.
 
-        Makes a copy of the un-compiled model definition to use for
-        compilation and fitting, leaving the original definition
-        intact.
+        # Arguments
+            X : array-like, shape `(n_samples, n_features)`
+                Training samples where n_samples in the number of samples
+                and n_features is the number of features.
+            y : array-like, shape `(n_samples,)` or `(n_samples, n_outputs)`
+                True labels for X.
+            kwargs: dictionary arguments
+                Legal arguments are the arguments of `Sequential.fit`
 
-        Parameters
-        ----------
-        X : array-like, shape = (n_samples, n_features)
-            Training samples where n_samples in the number of samples
-            and n_features is the number of features.
-        y : array-like, shape = (n_samples) or (n_samples, n_outputs)
-            True labels for X.
+        # Returns
+            history : object
+                details about the training history at each epoch.
+        '''
 
-        Returns
-        -------
-        history : object
-            Returns details about the training history at each epoch.
-        """
-        if len(y.shape) == 1:
-            self.classes_ = list(np.unique(y))
-            if self.loss == 'categorical_crossentropy':
-                y = to_categorical(y)
+        if self.build_fn is None:
+            self.model = self.__call__(**self.filter_sk_params(self.__call__))
+        elif not isinstance(self.build_fn, types.FunctionType):
+            self.model = self.build_fn(
+                **self.filter_sk_params(self.build_fn.__call__))
         else:
-            self.classes_ = np.arange(0, y.shape[1])
+            self.model = self.build_fn(**self.filter_sk_params(self.build_fn))
 
-        self.compiled_model_ = copy.deepcopy(self.model)
-        self.compiled_model_.compile(optimizer=self.optimizer, loss=self.loss)
-        history = self.compiled_model_.fit(
-            X, y, batch_size=self.train_batch_size, nb_epoch=self.nb_epoch, verbose=self.verbose,
-            shuffle=self.shuffle, show_accuracy=self.show_accuracy,
-            validation_split=self.validation_split, validation_data=self.validation_data,
-            callbacks=self.callbacks)
+        loss_name = self.model.loss
+        if hasattr(loss_name, '__name__'):
+            loss_name = loss_name.__name__
+        if loss_name == 'categorical_crossentropy' and len(y.shape) != 2:
+            y = to_categorical(y)
 
-        self.config_ = self.model.get_config()
-        self.weights_ = self.model.get_weights()
+        fit_args = copy.deepcopy(self.filter_sk_params(Sequential.fit))
+        fit_args.update(kwargs)
+
+        history = self.model.fit(X, y, **fit_args)
 
         return history
 
+    def filter_sk_params(self, fn, override={}):
+        '''Filter sk_params and return those in fn's arguments
+
+        # Arguments
+            fn : arbitrary function
+            override: dictionary, values to overrid sk_params
+
+        # Returns
+            res : dictionary dictionary containing variabls
+                in both sk_params and fn's arguments.
+        '''
+        res = {}
+        fn_args = inspect.getargspec(fn)[0]
+        for name, value in self.sk_params.items():
+            if name in fn_args:
+                res.update({name: value})
+        res.update(override)
+        return res
+
 
 class KerasClassifier(BaseWrapper):
-    """
-    Implementation of the scikit-learn classifier API for Keras.
+    '''Implementation of the scikit-learn classifier API for Keras.
+    '''
 
-    Parameters
-    ----------
-    model : object
-        An un-compiled Keras model object is required to use the scikit-learn wrapper.
-    optimizer : string
-        Optimization method used by the model during compilation/training.
-    loss : string
-        Loss function used by the model during compilation/training.
-    """
-    def __init__(self, model, optimizer='adam', loss='categorical_crossentropy', **kwargs):
-        super(KerasClassifier, self).__init__(model, optimizer, loss, **kwargs)
+    def predict(self, X, **kwargs):
+        '''Returns the class predictions for the given test data.
 
-    def predict(self, X):
-        """
-        Returns the class predictions for the given test data.
+        # Arguments
+            X: array-like, shape `(n_samples, n_features)`
+                Test samples where n_samples in the number of samples
+                and n_features is the number of features.
+            kwargs: dictionary arguments
+                Legal arguments are the arguments of `Sequential.predict_classes`.
 
-        Parameters
-        ----------
-        X : array-like, shape = (n_samples, n_features)
-            Test samples where n_samples in the number of samples
-            and n_features is the number of features.
+        # Returns
+            preds: array-like, shape `(n_samples,)`
+                Class predictions.
+        '''
+        kwargs = self.filter_sk_params(Sequential.predict_classes, kwargs)
+        return self.model.predict_classes(X, **kwargs)
 
-        Returns
-        -------
-        preds : array-like, shape = (n_samples)
-            Class predictions.
-        """
-        return self.compiled_model_.predict_classes(
-            X, batch_size=self.test_batch_size, verbose=self.verbose)
+    def predict_proba(self, X, **kwargs):
+        '''Returns class probability estimates for the given test data.
 
-    def predict_proba(self, X):
-        """
-        Returns class probability estimates for the given test data.
+        # Arguments
+            X: array-like, shape `(n_samples, n_features)`
+                Test samples where n_samples in the number of samples
+                and n_features is the number of features.
+            kwargs: dictionary arguments
+                Legal arguments are the arguments of `Sequential.predict_classes`.
 
-        Parameters
-        ----------
-        X : array-like, shape = (n_samples, n_features)
-            Test samples where n_samples in the number of samples
-            and n_features is the number of features.
+        # Returns
+            proba: array-like, shape `(n_samples, n_outputs)`
+                Class probability estimates.
+        '''
+        kwargs = self.filter_sk_params(Sequential.predict_proba, kwargs)
+        return self.model.predict_proba(X, **kwargs)
 
-        Returns
-        -------
-        proba : array-like, shape = (n_samples, n_outputs)
-            Class probability estimates.
-        """
-        return self.compiled_model_.predict_proba(
-            X, batch_size=self.test_batch_size, verbose=self.verbose)
+    def score(self, X, y, **kwargs):
+        '''Returns the mean accuracy on the given test data and labels.
 
-    def score(self, X, y):
-        """
-        Returns the mean accuracy on the given test data and labels.
+        # Arguments
+            X: array-like, shape `(n_samples, n_features)`
+                Test samples where n_samples in the number of samples
+                and n_features is the number of features.
+            y: array-like, shape `(n_samples,)` or `(n_samples, n_outputs)`
+                True labels for X.
+            kwargs: dictionary arguments
+                Legal arguments are the arguments of `Sequential.evaluate`.
 
-        Parameters
-        ----------
-        X : array-like, shape = (n_samples, n_features)
-            Test samples where n_samples in the number of samples
-            and n_features is the number of features.
-        y : array-like, shape = (n_samples) or (n_samples, n_outputs)
-            True labels for X.
-
-        Returns
-        -------
-        score : float
-            Mean accuracy of predictions on X wrt. y.
-        """
-        loss, accuracy = self.compiled_model_.evaluate(
-            X, y, batch_size=self.test_batch_size, show_accuracy=True, verbose=self.verbose)
-        return accuracy
+        # Returns
+            score: float
+                Mean accuracy of predictions on X wrt. y.
+        '''
+        kwargs = self.filter_sk_params(Sequential.evaluate, kwargs)
+        outputs = self.model.evaluate(X, y, **kwargs)
+        if type(outputs) is not list:
+            outputs = [outputs]
+        for name, output in zip(self.model.metrics_names, outputs):
+            if name == 'acc':
+                return output
+        raise Exception('The model is not configured to compute accuracy. '
+                        'You should pass `metrics=["accuracy"]` to '
+                        'the `model.compile()` method.')
 
 
 class KerasRegressor(BaseWrapper):
-    """
-    Implementation of the scikit-learn regressor API for Keras.
+    '''Implementation of the scikit-learn regressor API for Keras.
+    '''
 
-    Parameters
-    ----------
-    model : object
-        An un-compiled Keras model object is required to use the scikit-learn wrapper.
-    optimizer : string
-        Optimization method used by the model during compilation/training.
-    loss : string
-        Loss function used by the model during compilation/training.
-    """
-    def __init__(self, model, optimizer='adam', loss='mean_squared_error', **kwargs):
-        super(KerasRegressor, self).__init__(model, optimizer, loss, **kwargs)
+    def predict(self, X, **kwargs):
+        '''Returns predictions for the given test data.
 
-    def predict(self, X):
-        """
-        Returns predictions for the given test data.
+        # Arguments
+            X: array-like, shape `(n_samples, n_features)`
+                Test samples where n_samples in the number of samples
+                and n_features is the number of features.
+            kwargs: dictionary arguments
+                Legal arguments are the arguments of `Sequential.predict`.
+        # Returns
+            preds: array-like, shape `(n_samples,)`
+                Predictions.
+        '''
+        kwargs = self.filter_sk_params(Sequential.predict, kwargs)
+        return self.model.predict(X, **kwargs)
 
-        Parameters
-        ----------
-        X : array-like, shape = (n_samples, n_features)
-            Test samples where n_samples in the number of samples
-            and n_features is the number of features.
+    def score(self, X, y, **kwargs):
+        '''Returns the mean loss on the given test data and labels.
 
-        Returns
-        -------
-        preds : array-like, shape = (n_samples)
-            Predictions.
-        """
-        return self.compiled_model_.predict(
-            X, batch_size=self.test_batch_size, verbose=self.verbose).ravel()
+        # Arguments
+            X: array-like, shape `(n_samples, n_features)`
+                Test samples where n_samples in the number of samples
+                and n_features is the number of features.
+            y: array-like, shape `(n_samples,)`
+                True labels for X.
+            kwargs: dictionary arguments
+                Legal arguments are the arguments of `Sequential.evaluate`.
 
-    def score(self, X, y):
-        """
-        Returns the mean accuracy on the given test data and labels.
-
-        Parameters
-        ----------
-        X : array-like, shape = (n_samples, n_features)
-            Test samples where n_samples in the number of samples
-            and n_features is the number of features.
-        y : array-like, shape = (n_samples)
-            True labels for X.
-
-        Returns
-        -------
-        score : float
-            Loss from predictions on X wrt. y.
-        """
-        loss = self.compiled_model_.evaluate(
-            X, y, batch_size=self.test_batch_size, show_accuracy=False, verbose=self.verbose)
+        # Returns
+            score: float
+                Mean accuracy of predictions on X wrt. y.
+        '''
+        kwargs = self.filter_sk_params(Sequential.evaluate, kwargs)
+        loss = self.model.evaluate(X, y, **kwargs)
+        if type(loss) is list:
+            return loss[0]
         return loss

setup.py

@@ -3,12 +3,12 @@ from setuptools import find_packages
 
 
 setup(name='Keras',
-      version='0.3.1',
-      description='Theano-based Deep Learning library',
+      version='1.0.3',
+      description='Deep Learning for Python',
       author='Francois Chollet',
       author_email='francois.chollet@gmail.com',
       url='https://github.com/fchollet/keras',
-      download_url='https://github.com/fchollet/keras/tarball/0.3.1',
+      download_url='https://github.com/fchollet/keras/tarball/1.0.3',
       license='MIT',
       install_requires=['theano', 'pyyaml', 'six'],
       extras_require={

tests/integration_tests/test_image_data_tasks.py

@@ -35,10 +35,12 @@ def test_image_classification():
         Activation('relu'),
         Dense(y_test.shape[-1], activation='softmax')
     ])
-    model.compile(loss='categorical_crossentropy', optimizer='sgd')
+    model.compile(loss='categorical_crossentropy',
+                  optimizer='rmsprop',
+                  metrics=['accuracy'])
     history = model.fit(X_train, y_train, nb_epoch=10, batch_size=16,
                         validation_data=(X_test, y_test),
-                        show_accuracy=True, verbose=0)
+                        verbose=0)
     assert(history.history['val_acc'][-1] > 0.85)
 
 

tests/integration_tests/test_temporal_data_tasks.py

@@ -4,21 +4,26 @@ import pytest
 import string
 
 from keras.utils.test_utils import get_test_data
-from keras.models import Sequential
-from keras.layers.core import TimeDistributedDense, Dropout, Dense, Activation
-from keras.layers.recurrent import GRU, LSTM
-from keras.layers.embeddings import Embedding
 from keras.utils.np_utils import to_categorical
+from keras.models import Sequential
+from keras.layers import TimeDistributedDense
+from keras.layers import Dense
+from keras.layers import Activation
+from keras.layers import GRU
+from keras.layers import LSTM
+from keras.layers import Embedding
 
 
 def test_temporal_classification():
     '''
-    Classify temporal sequences of float numbers of length 3 into 2 classes using
-    single layer of GRU units and softmax applied to the last activations of the units
+    Classify temporal sequences of float numbers
+    of length 3 into 2 classes using
+    single layer of GRU units and softmax applied
+    to the last activations of the units
     '''
     np.random.seed(1337)
     (X_train, y_train), (X_test, y_test) = get_test_data(nb_train=500,
-                                                         nb_test=200,
+                                                         nb_test=500,
                                                          input_shape=(3, 5),
                                                          classification=True,
                                                          nb_class=2)
@@ -29,11 +34,13 @@ def test_temporal_classification():
     model.add(GRU(y_train.shape[-1],
                   input_shape=(X_train.shape[1], X_train.shape[2]),
                   activation='softmax'))
-    model.compile(loss='categorical_crossentropy', optimizer='adadelta')
-    history = model.fit(X_train, y_train, nb_epoch=5, batch_size=16,
+    model.compile(loss='categorical_crossentropy',
+                  optimizer='adagrad',
+                  metrics=['accuracy'])
+    history = model.fit(X_train, y_train, nb_epoch=20, batch_size=32,
                         validation_data=(X_test, y_test),
-                        show_accuracy=True, verbose=0)
-    assert(history.history['val_acc'][-1] > 0.9)
+                        verbose=0)
+    assert(history.history['val_acc'][-1] >= 0.85)
 
 
 def test_temporal_regression():
@@ -142,12 +149,12 @@ def test_masked_temporal():
     '''
     np.random.seed(55318)
     model = Sequential()
-    model.add(Embedding(10, 20, mask_zero=True))
+    model.add(Embedding(10, 20, mask_zero=True, input_length=20))
     model.add(TimeDistributedDense(10))
     model.add(Activation('softmax'))
     model.compile(loss='categorical_crossentropy',
                   optimizer='adam',
-                  sample_weight_mode="temporal")
+                  sample_weight_mode='temporal')
 
     X = np.random.random_integers(1, 9, (50000, 20))
     for rowi in range(X.shape[0]):
@@ -164,15 +171,16 @@ def test_masked_temporal():
 
     # Mask 50% of the outputs via sample weights
     sample_weight = np.random.random_integers(0, 1, y.shape)
-    print("X shape: ", X.shape)
-    print("Y shape: ", Y.shape)
-    print("sample_weight shape: ", Y.shape)
+    print('X shape:', X.shape)
+    print('Y shape:', Y.shape)
+    print('sample_weight shape:', Y.shape)
 
     history = model.fit(X, Y, validation_split=0.05,
-                        sample_weight=sample_weight,
+                        sample_weight=None,
                         verbose=1, nb_epoch=2)
     ground_truth = -np.log(0.5)
-    assert(np.abs(history.history['val_loss'][-1] - ground_truth) < 0.05)
+    assert(np.abs(history.history['val_loss'][-1] - ground_truth) < 0.06)
 
 if __name__ == '__main__':
-    pytest.main([__file__])
+    # pytest.main([__file__])
+    test_temporal_classification()

tests/integration_tests/test_vector_data_tasks.py

@@ -28,10 +28,12 @@ def test_vector_classification():
         Dense(nb_hidden, input_shape=(X_train.shape[-1],), activation='relu'),
         Dense(y_train.shape[-1], activation='softmax')
     ])
-    model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
+    model.compile(loss='categorical_crossentropy',
+                  optimizer='rmsprop',
+                  metrics=['accuracy'])
     history = model.fit(X_train, y_train, nb_epoch=15, batch_size=16,
                         validation_data=(X_test, y_test),
-                        show_accuracy=True, verbose=0)
+                        verbose=0)
     assert(history.history['val_acc'][-1] > 0.8)
 
 

tests/keras/backend/test_backends.py

@@ -5,6 +5,7 @@ import numpy as np
 
 from keras.backend import theano_backend as KTH
 from keras.backend import tensorflow_backend as KTF
+from keras.utils.np_utils import convert_kernel
 
 
 def check_single_tensor_operation(function_name, input_shape, **kwargs):
@@ -22,10 +23,12 @@ def check_single_tensor_operation(function_name, input_shape, **kwargs):
 def check_two_tensor_operation(function_name, x_input_shape,
                                y_input_shape, **kwargs):
     xval = np.random.random(x_input_shape) - 0.5
+
     xth = KTH.variable(xval)
     xtf = KTF.variable(xval)
 
     yval = np.random.random(y_input_shape) - 0.5
+
     yth = KTH.variable(yval)
     ytf = KTF.variable(yval)
 
@@ -40,6 +43,10 @@ class TestBackend(object):
 
     def test_linear_operations(self):
         check_two_tensor_operation('dot', (4, 2), (2, 4))
+        check_two_tensor_operation('dot', (4, 2), (5, 2, 3))
+
+        check_two_tensor_operation('batch_dot', (4, 2, 3), (4, 5, 3),
+                                   axes=(2, 2))
         check_single_tensor_operation('transpose', (4, 2))
 
     def test_shape_operations(self):
@@ -84,6 +91,17 @@ class TestBackend(object):
                 assert_allclose(np_rep, th_rep, atol=1e-05)
                 assert_allclose(np_rep, tf_rep, atol=1e-05)
 
+    def test_tile(self):
+        shape = (3, 4)
+        arr = np.arange(np.prod(shape)).reshape(shape)
+        arr_th = KTH.variable(arr)
+        arr_tf = KTF.variable(arr)
+
+        n = (2, 1)
+        th_rep = KTH.eval(KTH.tile(arr_th, n))
+        tf_rep = KTF.eval(KTF.tile(arr_tf, n))
+        assert_allclose(tf_rep, th_rep, atol=1e-05)
+
     def test_value_manipulation(self):
         val = np.random.random((4, 2))
         xth = KTH.variable(val)
@@ -145,6 +163,7 @@ class TestBackend(object):
         check_single_tensor_operation('exp', (4, 2))
         check_single_tensor_operation('log', (4, 2))
         check_single_tensor_operation('round', (4, 2))
+        check_single_tensor_operation('sign', (4, 2))
         check_single_tensor_operation('pow', (4, 2), a=3)
         check_single_tensor_operation('clip', (4, 2), min_value=0.4,
                                       max_value=0.6)
@@ -222,10 +241,10 @@ class TestBackend(object):
             return step_function
 
         th_rnn_step_fn = rnn_step_fn(input_dim, output_dim, KTH)
-        inputs = KTH.variable(input_val)
-        initial_states = [KTH.variable(init_state_val)]
-        last_output, outputs, new_states = KTH.rnn(th_rnn_step_fn, inputs,
-                                                   initial_states,
+        th_inputs = KTH.variable(input_val)
+        th_initial_states = [KTH.variable(init_state_val)]
+        last_output, outputs, new_states = KTH.rnn(th_rnn_step_fn, th_inputs,
+                                                   th_initial_states,
                                                    go_backwards=False,
                                                    mask=None)
         th_last_output = KTH.eval(last_output)
@@ -234,10 +253,10 @@ class TestBackend(object):
         th_state = KTH.eval(new_states[0])
 
         tf_rnn_step_fn = rnn_step_fn(input_dim, output_dim, KTF)
-        inputs = KTF.variable(input_val)
-        initial_states = [KTF.variable(init_state_val)]
-        last_output, outputs, new_states = KTF.rnn(tf_rnn_step_fn, inputs,
-                                                   initial_states,
+        tf_inputs = KTF.variable(input_val)
+        tf_initial_states = [KTF.variable(init_state_val)]
+        last_output, outputs, new_states = KTF.rnn(tf_rnn_step_fn, tf_inputs,
+                                                   tf_initial_states,
                                                    go_backwards=False,
                                                    mask=None)
         tf_last_output = KTF.eval(last_output)
@@ -249,6 +268,80 @@ class TestBackend(object):
         assert_allclose(tf_outputs, th_outputs, atol=1e-04)
         assert_allclose(tf_state, th_state, atol=1e-04)
 
+        # test unroll
+        unrolled_last_output, unrolled_outputs, unrolled_new_states = KTH.rnn(
+            th_rnn_step_fn, th_inputs,
+            th_initial_states,
+            go_backwards=False,
+            mask=None,
+            unroll=True,
+            input_length=timesteps)
+
+        unrolled_th_last_output = KTH.eval(unrolled_last_output)
+        unrolled_th_outputs = KTH.eval(unrolled_outputs)
+        assert len(unrolled_new_states) == 1
+        unrolled_th_state = KTH.eval(unrolled_new_states[0])
+        assert_allclose(th_last_output, unrolled_th_last_output, atol=1e-04)
+        assert_allclose(th_outputs, unrolled_th_outputs, atol=1e-04)
+        assert_allclose(th_state, unrolled_th_state, atol=1e-04)
+
+        # test unroll with backwards = True
+        bwd_last_output, bwd_outputs, bwd_new_states = KTH.rnn(
+            th_rnn_step_fn, th_inputs,
+            th_initial_states,
+            go_backwards=True,
+            mask=None)
+        bwd_th_last_output = KTH.eval(bwd_last_output)
+        bwd_th_outputs = KTH.eval(bwd_outputs)
+        assert len(bwd_new_states) == 1
+        bwd_th_state = KTH.eval(bwd_new_states[0])
+
+        bwd_unrolled_last_output, bwd_unrolled_outputs, bwd_unrolled_new_states = KTH.rnn(
+            th_rnn_step_fn, th_inputs,
+            th_initial_states,
+            go_backwards=True,
+            mask=None,
+            unroll=True,
+            input_length=timesteps)
+
+        bwd_unrolled_th_last_output = KTH.eval(bwd_unrolled_last_output)
+        bwd_unrolled_th_outputs = KTH.eval(bwd_unrolled_outputs)
+        assert len(bwd_unrolled_new_states) == 1
+        bwd_unrolled_th_state = KTH.eval(bwd_unrolled_new_states[0])
+        assert_allclose(bwd_th_last_output, bwd_unrolled_th_last_output, atol=1e-04)
+        assert_allclose(bwd_th_outputs, bwd_unrolled_th_outputs, atol=1e-04)
+        assert_allclose(bwd_th_state, bwd_unrolled_th_state, atol=1e-04)
+
+        # test unroll with masking
+        np_mask = np.random.randint(2, size=(32, timesteps))
+        th_mask = KTH.variable(np_mask)
+
+        masked_last_output, masked_outputs, masked_new_states = KTH.rnn(
+            th_rnn_step_fn, th_inputs,
+            th_initial_states,
+            go_backwards=False,
+            mask=th_mask)
+        masked_th_last_output = KTH.eval(masked_last_output)
+        masked_th_outputs = KTH.eval(masked_outputs)
+        assert len(masked_new_states) == 1
+        masked_th_state = KTH.eval(masked_new_states[0])
+
+        unrolled_masked_last_output, unrolled_masked_outputs, unrolled_masked_new_states = KTH.rnn(
+            th_rnn_step_fn, th_inputs,
+            th_initial_states,
+            go_backwards=False,
+            mask=th_mask,
+            unroll=True,
+            input_length=timesteps)
+        unrolled_masked_th_last_output = KTH.eval(unrolled_masked_last_output)
+        unrolled_masked_th_outputs = KTH.eval(unrolled_masked_outputs)
+        assert len(unrolled_masked_new_states) == 1
+        unrolled_masked_th_state = KTH.eval(unrolled_masked_new_states[0])
+
+        assert_allclose(unrolled_masked_th_last_output, masked_th_last_output, atol=1e-04)
+        assert_allclose(unrolled_masked_th_outputs, masked_th_outputs, atol=1e-04)
+        assert_allclose(unrolled_masked_th_state, masked_th_state, atol=1e-04)
+
     def test_switch(self):
         val = np.random.random()
         xth = KTH.variable(val)
@@ -273,7 +366,7 @@ class TestBackend(object):
         check_single_tensor_operation('tanh', (4, 2))
 
         # dropout
-        val = np.random.random((20, 20))
+        val = np.random.random((100, 100))
         xth = KTH.variable(val)
         xtf = KTF.variable(val)
         zth = KTH.eval(KTH.dropout(xth, level=0.2))
@@ -290,42 +383,56 @@ class TestBackend(object):
         check_single_tensor_operation('l2_normalize', (4, 3), axis=-1)
         check_single_tensor_operation('l2_normalize', (4, 3), axis=1)
 
-    # def test_conv2d(self):
-    #     '''conv2d works "properly" with Theano and TF but outputs different
-    #     values in each case. Cause unclear (input / kernel shape format?)
-    #     '''
-    #     # TH kernel shape: (depth, input_depth, rows, cols)
-    #     check_two_tensor_operation('conv2d', (5, 3, 10, 12), (4, 3, 2, 2),
-    #                                strides=(1, 1), border_mode='valid')
-    #     check_two_tensor_operation('conv2d', (5, 3, 10, 12), (4, 3, 2, 2),
-    #                                strides=(1, 1), border_mode='same')
+    def test_conv2d(self):
+        # TH kernel shape: (depth, input_depth, rows, cols)
+        # TF kernel shape: (rows, cols, input_depth, depth)
 
-    #     # TF kernel shape: (rows, cols, input_depth, depth)
-    #     check_two_tensor_operation('conv2d', (5, 10, 12, 3), (2, 2, 3, 4),
-    #                                strides=(1, 1), border_mode='valid', dim_ordering='tf')
-    #     check_two_tensor_operation('conv2d', (5, 10, 12, 3), (2, 2, 3, 4),
-    #                                strides=(1, 1), border_mode='same', dim_ordering='tf')
+        for input_shape in [(2, 3, 4, 5), (2, 3, 5, 6)]:
+            for kernel_shape in [(4, 3, 2, 2), (4, 3, 3, 4)]:
+                xval = np.random.random(input_shape)
 
-    #     check_two_tensor_operation('conv2d', (5, 3, 10, 12), (4, 3, 3, 3),
-    #                                strides=(1, 1), border_mode='valid')
-    #     check_two_tensor_operation('conv2d', (5, 3, 10, 12), (4, 3, 3, 3),
-    #                                strides=(1, 1), border_mode='same')
+                xth = KTH.variable(xval)
+                xtf = KTF.variable(xval)
 
-    #     check_two_tensor_operation('conv2d', (5, 3, 10, 12), (4, 3, 3, 3),
-    #                                strides=(2, 2), border_mode='valid')
+                kernel_val = np.random.random(kernel_shape) - 0.5
 
-    # def test_pool2d(self):
-    #     '''pool2d works "properly" with Theano and TF but outputs different
-    #     values in each case. Cause unclear (input shape format?)
-    #     '''
-    #     check_single_tensor_operation('pool2d', (5, 3, 10, 12), pool_size=(2, 2),
-    #                                   strides=(1, 1), border_mode='valid')
+                kernel_th = KTH.variable(convert_kernel(kernel_val))
+                kernel_tf = KTF.variable(kernel_val)
 
-    #     check_single_tensor_operation('pool2d', (5, 3, 9, 11), pool_size=(2, 2),
-    #                                   strides=(1, 1), border_mode='valid')
+                zth = KTH.eval(KTH.conv2d(xth, kernel_th))
+                ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf))
 
-    #     check_single_tensor_operation('pool2d', (5, 3, 9, 11), pool_size=(2, 3),
-    #                                   strides=(1, 1), border_mode='valid')
+                assert zth.shape == ztf.shape
+                assert_allclose(zth, ztf, atol=1e-05)
+
+        input_shape = (1, 6, 5, 3)
+        kernel_shape = (3, 3, 3, 2)
+
+        xval = np.random.random(input_shape)
+
+        xth = KTH.variable(xval)
+        xtf = KTF.variable(xval)
+
+        kernel_val = np.random.random(kernel_shape) - 0.5
+
+        kernel_th = KTH.variable(convert_kernel(kernel_val, dim_ordering='tf'))
+        kernel_tf = KTF.variable(kernel_val)
+
+        zth = KTH.eval(KTH.conv2d(xth, kernel_th, dim_ordering='tf'))
+        ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf, dim_ordering='tf'))
+
+        assert zth.shape == ztf.shape
+        assert_allclose(zth, ztf, atol=1e-05)
+
+    def test_pool2d(self):
+        check_single_tensor_operation('pool2d', (5, 3, 10, 12), pool_size=(2, 2),
+                                      strides=(1, 1), border_mode='valid')
+
+        check_single_tensor_operation('pool2d', (5, 3, 9, 11), pool_size=(2, 2),
+                                      strides=(1, 1), border_mode='valid')
+
+        check_single_tensor_operation('pool2d', (5, 3, 9, 11), pool_size=(2, 3),
+                                      strides=(1, 1), border_mode='valid')
 
     def test_random_normal(self):
         mean = 0.
@@ -355,6 +462,20 @@ class TestBackend(object):
         assert(np.max(rand) <= max)
         assert(np.min(rand) >= min)
 
+    def test_random_binomial(self):
+        p = 0.5
+        rand = KTF.eval(KTF.random_binomial((1000, 1000), p))
+        assert(rand.shape == (1000, 1000))
+        assert(np.abs(np.mean(rand) - p) < 0.01)
+        assert(np.max(rand) == 1)
+        assert(np.min(rand) == 0)
+
+        rand = KTH.eval(KTH.random_binomial((1000, 1000), p))
+        assert(rand.shape == (1000, 1000))
+        assert(np.abs(np.mean(rand) - p) < 0.01)
+        assert(np.max(rand) == 1)
+        assert(np.min(rand) == 0)
+
 
 if __name__ == '__main__':
     pytest.main([__file__])