Update backend docs.

keras/backend/cntk_backend.py

@@ -1,7 +1,7 @@
 from __future__ import print_function
 import cntk as C
 import numpy as np
-from .common import _FLOATX, _EPSILON, image_dim_ordering, image_data_format
+from .common import floatx, epsilon, image_dim_ordering, image_data_format
 from collections import defaultdict
 from contextlib import contextmanager
 import warnings
@@ -130,7 +130,10 @@ def _convert_dtype_string(dtype):
                          'float64.' % dtype)
 
 
-def variable(value, dtype=_FLOATX, name=None):
+def variable(value, dtype=None, name=None):
+    if dtype is None:
+        dtype = floatx()
+
     if name is None:
         name = ''
 
@@ -227,10 +230,12 @@ def eval(x):
 def placeholder(
         shape=None,
         ndim=None,
-        dtype=_FLOATX,
+        dtype=None,
         sparse=False,
         name=None,
         dynamic_axis_num=1):
+    if dtype is None:
+        dtype = floatx()
     if not shape:
         if ndim:
             shape = tuple([None for _ in range(ndim)])
@@ -304,7 +309,7 @@ def _prepare_name(name, default):
 
 def constant(value, dtype=None, shape=None, name=None):
     if dtype is None:
-        dtype = _FLOATX
+        dtype = floatx()
     if shape is None:
         shape = ()
     np_value = value * np.ones(shape)
@@ -351,8 +356,10 @@ def random_uniform(shape, minval=0.0, maxval=1.0, dtype=None, seed=None):
     return random_uniform_variable(shape, minval, maxval, dtype, seed)
 
 
-def random_uniform_variable(shape, low, high, dtype=_FLOATX,
-                            name=None, seed=None):
+def random_uniform_variable(shape, low, high,
+                            dtype=None, name=None, seed=None):
+    if dtype is None:
+        dtype = floatx()
     if seed is None:
         # ensure that randomness is conditioned by the Numpy RNG
         seed = np.random.randint(10e3)
@@ -380,9 +387,11 @@ def random_normal_variable(
         shape,
         mean,
         scale,
-        dtype=_FLOATX,
+        dtype=None,
         name=None,
         seed=None):
+    if dtype is None:
+        dtype = floatx()
     if seed is None:
         # ensure that randomness is conditioned by the Numpy RNG
         seed = np.random.randint(10e7)
@@ -403,7 +412,9 @@ def random_normal_variable(
         name=name)
 
 
-def random_normal(shape, mean=0.0, stddev=1.0, dtype=_FLOATX, seed=None):
+def random_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
+    if dtype is None:
+        dtype = floatx()
     for _ in shape:
         if _ is None:
             raise ValueError('CNTK Backend: randomness op with '
@@ -435,17 +446,23 @@ def dtype(x):
     return _convert_dtype_string(x.dtype)
 
 
-def zeros(shape, dtype=_FLOATX, name=None):
+def zeros(shape, dtype=None, name=None):
+    if dtype is None:
+        dtype = floatx()
     ctype = _convert_string_dtype(dtype)
     return variable(value=np.zeros(shape, ctype), dtype=dtype, name=name)
 
 
-def ones(shape, dtype=_FLOATX, name=None):
+def ones(shape, dtype=None, name=None):
+    if dtype is None:
+        dtype = floatx()
     ctype = _convert_string_dtype(dtype)
     return variable(value=np.ones(shape, ctype), dtype=dtype, name=name)
 
 
-def eye(size, dtype=_FLOATX, name=None):
+def eye(size, dtype=None, name=None):
+    if dtype is None:
+        dtype = floatx()
     return variable(np.eye(size), dtype, name)
 
 
@@ -729,7 +746,7 @@ def all(x, axis=None, keepdims=False):
         return all_matrix
 
 
-def classification_error(output, target, axis=-1):
+def classification_error(target, output, axis=-1):
     return C.ops.reduce_mean(
         C.equal(
             argmax(
@@ -801,10 +818,10 @@ def clip(x, min_value, max_value):
     return C.clip(x, min_value, max_value)
 
 
-def binary_crossentropy(output, target, from_logits=False):
+def binary_crossentropy(target, output, from_logits=False):
     if from_logits:
         output = C.sigmoid(output)
-    output = C.clip(output, _EPSILON, 1.0 - _EPSILON)
+    output = C.clip(output, epsilon(), 1.0 - epsilon())
     output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
     return output
 
@@ -1522,7 +1539,7 @@ def softsign(x):
     return x / (1 + C.abs(x))
 
 
-def categorical_crossentropy(output, target, from_logits=False):
+def categorical_crossentropy(target, output, from_logits=False):
     if from_logits:
         result = C.cross_entropy_with_softmax(output, target)
         # cntk's result shape is (batch, 1), while keras expect (batch, )
@@ -1530,18 +1547,19 @@ def categorical_crossentropy(output, target, from_logits=False):
     else:
         # scale preds so that the class probas of each sample sum to 1
         output /= C.reduce_sum(output, axis=-1)
-        # avoid numerical instability with _EPSILON clipping
-        output = C.clip(output, _EPSILON, 1.0 - _EPSILON)
+        # avoid numerical instability with epsilon clipping
+        output = C.clip(output, epsilon(), 1.0 - epsilon())
         return -sum(target * C.log(output), axis=-1)
 
 
-def sparse_categorical_crossentropy(output, target, from_logits=False):
+def sparse_categorical_crossentropy(target, output, from_logits=False):
     target = C.one_hot(target, output.shape[-1])
     target = C.reshape(target, output.shape)
     return categorical_crossentropy(output, target, from_logits)
 
 
 class Function(object):
+
     def __init__(self, inputs, outputs, updates=[], **kwargs):
         self.placeholders = inputs
         self.trainer = None
@@ -1578,11 +1596,12 @@ class Function(object):
                     p_list.append(grad_parameter_dict[g])
                     u_list.append(g)
                 else:
-                    raise ValueError('CNTK backend: when constructing trainer, '
-                                     'found gradient node `%s` which is not '
-                                     'related to any parameters in the model. '
-                                     'Please double check how the gradient node '
-                                     'is constructed.' % g)
+                    raise ValueError(
+                        'CNTK backend: when constructing trainer, '
+                        'found gradient node `%s` which is not '
+                        'related to any parameters in the model. '
+                        'Please double check how the gradient node '
+                        'is constructed.' % g)
 
             if len(u_list) > 0:
                 learner = C.cntk_py.universal_learner(p_list, u_list, update_func)
@@ -1635,11 +1654,12 @@ class Function(object):
             # in current version cntk can't support input with variable
             # length. Will support it in next release.
             if not self._is_input_shape_compatible(value, tensor):
-                raise ValueError('CNTK backend: The placeholder has been resolved '
-                                 'to shape `%s`, but input shape is `%s`. Currently '
-                                 'CNTK can not take variable length inputs. Please '
-                                 'pass inputs that have a static shape.'
-                                 % (tensor.shape, value.shape))
+                raise ValueError(
+                    'CNTK backend: The placeholder has been resolved '
+                    'to shape `%s`, but input shape is `%s`. Currently '
+                    'CNTK can not take variable length inputs. Please '
+                    'pass inputs that have a static shape.'
+                    % (tensor.shape, value.shape))
             feed_dict[tensor] = value
 
         updated = []
@@ -1649,9 +1669,10 @@ class Function(object):
                 if argument in feed_dict:
                     input_dict[argument] = feed_dict[argument]
                 else:
-                    raise ValueError('CNTK backend: argument %s is not found in inputs. '
-                                     'Please double check the model and inputs in '
-                                     '`train_function`.' % argument.name)
+                    raise ValueError(
+                        'CNTK backend: argument %s is not found in inputs. '
+                        'Please double check the model and inputs in '
+                        '`train_function`.' % argument.name)
 
             result = self.trainer.train_minibatch(
                 input_dict, self.trainer_output)
@@ -1667,9 +1688,10 @@ class Function(object):
                 if argument in feed_dict:
                     input_dict[argument] = feed_dict[argument]
                 else:
-                    raise ValueError('CNTK backend: metrics argument %s '
-                                     'is not found in inputs. Please double '
-                                     'check the model and inputs.' % argument.name)
+                    raise ValueError(
+                        'CNTK backend: metrics argument %s '
+                        'is not found in inputs. Please double '
+                        'check the model and inputs.' % argument.name)
             output_values = self.metrics_func.eval(input_dict, as_numpy=False)
             if isinstance(output_values, dict):
                 for o in self.metrics_outputs:
@@ -1687,9 +1709,10 @@ class Function(object):
                 if argument in feed_dict:
                     input_dict[argument] = feed_dict[argument]
                 else:
-                    raise ValueError('CNTK backend: assign ops argument %s '
-                                     'is not found in inputs. Please double '
-                                     'check the model and inputs.' % argument.name)
+                    raise ValueError(
+                        'CNTK backend: assign ops argument %s '
+                        'is not found in inputs. Please double '
+                        'check the model and inputs.' % argument.name)
             self.unrelated_updates.eval(input_dict, as_numpy=False)
         return updated
 

keras/backend/tensorflow_backend.py

@@ -2722,14 +2722,14 @@ def softsign(x):
     return tf.nn.softsign(x)
 
 
-def categorical_crossentropy(output, target, from_logits=False):
+def categorical_crossentropy(target, output, from_logits=False):
     """Categorical crossentropy between an output tensor and a target tensor.
 
     # Arguments
+        target: A tensor of the same shape as `output`.
         output: A tensor resulting from a softmax
             (unless `from_logits` is True, in which
             case `output` is expected to be the logits).
-        target: A tensor of the same shape as `output`.
         from_logits: Boolean, whether `output` is the
             result of a softmax, or is a tensor of logits.
 
@@ -2753,14 +2753,14 @@ def categorical_crossentropy(output, target, from_logits=False):
                                                        logits=output)
 
 
-def sparse_categorical_crossentropy(output, target, from_logits=False):
+def sparse_categorical_crossentropy(target, output, from_logits=False):
     """Categorical crossentropy with integer targets.
 
     # Arguments
+        target: An integer tensor.
         output: A tensor resulting from a softmax
             (unless `from_logits` is True, in which
             case `output` is expected to be the logits).
-        target: An integer tensor.
         from_logits: Boolean, whether `output` is the
             result of a softmax, or is a tensor of logits.
 
@@ -2787,12 +2787,12 @@ def sparse_categorical_crossentropy(output, target, from_logits=False):
         return res
 
 
-def binary_crossentropy(output, target, from_logits=False):
+def binary_crossentropy(target, output, from_logits=False):
     """Binary crossentropy between an output tensor and a target tensor.
 
     # Arguments
-        output: A tensor.
         target: A tensor with the same shape as `output`.
+        output: A tensor.
         from_logits: Whether `output` is expected to be a logits tensor.
             By default, we consider that `output`
             encodes a probability distribution.

keras/backend/theano_backend.py

@@ -1,7 +1,6 @@
 from collections import defaultdict
 from contextlib import contextmanager
 import theano
-from theano import ifelse
 from theano import tensor as T
 from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
 from theano.tensor.signal import pool
@@ -1502,7 +1501,7 @@ def softsign(x):
     return T_softsign(x)
 
 
-def categorical_crossentropy(output, target, from_logits=False):
+def categorical_crossentropy(target, output, from_logits=False):
     if from_logits:
         output = T.nnet.softmax(output)
     else:
@@ -1513,14 +1512,14 @@ def categorical_crossentropy(output, target, from_logits=False):
     return T.nnet.categorical_crossentropy(output, target)
 
 
-def sparse_categorical_crossentropy(output, target, from_logits=False):
+def sparse_categorical_crossentropy(target, output, 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):
+def binary_crossentropy(target, output, from_logits=False):
     if from_logits:
         output = T.nnet.sigmoid(output)
     # avoid numerical instability with _EPSILON clipping
@@ -2355,9 +2354,8 @@ def foldl(fn, elems, initializer=None, name=None):
 
     # We need to change the order of the arguments because theano accepts x as
     # first parameter and accumulator as second
-    fn2 = lambda x, acc: fn(acc, x)
-
-    return theano.foldl(fn2, elems, initializer, name=name)[0]
+    return theano.foldl(lambda x, acc: fn(acc, x),
+                        elems, initializer, name=name)[0]
 
 
 def foldr(fn, elems, initializer=None, name=None):
@@ -2379,9 +2377,8 @@ def foldr(fn, elems, initializer=None, name=None):
 
     # We need to change the order of the arguments because theano accepts x as
     # first parameter and accumulator as second
-    fn2 = lambda x, acc: fn(acc, x)
-
-    return theano.foldr(fn2, elems, initializer, name=name)[0]
+    return theano.foldr(lambda x, acc: fn(acc, x),
+                        elems, initializer, name=name)[0]
 
 
 def local_conv1d(inputs, kernel, kernel_size, strides, data_format=None):
@@ -2449,5 +2446,4 @@ def local_conv2d(inputs, kernel, kernel_size, strides, output_shape, data_format
         output = reshape(output,
                          (output_row, output_col, -1, filters))
         output = permute_dimensions(output, (2, 0, 1, 3))
-
     return output

keras/losses.py

@@ -46,15 +46,15 @@ def logcosh(y_true, y_pred):
 
 
 def categorical_crossentropy(y_true, y_pred):
-    return K.categorical_crossentropy(y_pred, y_true)
+    return K.categorical_crossentropy(y_true, y_pred)
 
 
 def sparse_categorical_crossentropy(y_true, y_pred):
-    return K.sparse_categorical_crossentropy(y_pred, y_true)
+    return K.sparse_categorical_crossentropy(y_true, y_pred)
 
 
 def binary_crossentropy(y_true, y_pred):
-    return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
+    return K.mean(K.binary_crossentropy(y_true, y_pred), axis=-1)
 
 
 def kullback_leibler_divergence(y_true, y_pred):

tests/keras/backend/backend_test.py

@@ -131,11 +131,11 @@ def check_cross_entropy_with_valid_probability_distribution():
     yth = KTH.variable(yval)
     yc = KC.placeholder((4, 2))
 
-    ztf = KTF.eval(KTF.categorical_crossentropy(xtf, ytf, from_logits=True))
-    zth = KTH.eval(KTH.categorical_crossentropy(xth, yth, from_logits=True))
+    ztf = KTF.eval(KTF.categorical_crossentropy(ytf, xtf, from_logits=True))
+    zth = KTH.eval(KTH.categorical_crossentropy(yth, xth, from_logits=True))
 
     func_cntk = KC.function([xc, yc],
-                            [KC.categorical_crossentropy(xc, yc, from_logits=True), ])
+                            [KC.categorical_crossentropy(yc, xc, from_logits=True)])
     zc = func_cntk([xval, yval])
     # Keras function return a list, take the first output
     assert len(zc) == 1