updates

evaluate.py

@@ -1,3 +1,5 @@
+#! /usr/local/bin/python3
+
 import os
 import sys
 from math import sqrt
@@ -14,6 +16,8 @@ CLASSIFY = 0
 REGRESS = 1
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 
+IMAGE_SIZE = 128
+
 
 def RMSE(t, p):
     return round(sqrt(mean_squared_error(t, p)), 4)
@@ -73,9 +77,9 @@ def get_classifier_predictions(model, paths, labels):
     labels_p_r = []
     count = 0
     for i, path in enumerate(paths):
-        img = image.load_img(path, target_size=(96, 96))
+        img = image.load_img(path, target_size=(IMAGE_SIZE, IMAGE_SIZE))
         img = image.img_to_array(img) / 255
-        img = np.array(img).reshape((1, 96, 96, 3))
+        img = np.array(img).reshape((1, IMAGE_SIZE, IMAGE_SIZE, 3))
         labels_t_r.append(labels[i])
         labels_t.append(np.argmax(labels[i]))
         p = model.predict(img)
@@ -96,9 +100,9 @@ def get_regressor_predictions(model, paths, labels):
     arousal_p = []
     count = 0
     for i, path in enumerate(paths):
-        img = image.load_img(path, target_size=(96, 96))
+        img = image.load_img(path, target_size=(IMAGE_SIZE, IMAGE_SIZE))
         img = image.img_to_array(img) / 255
-        img = np.array(img).reshape((1, 96, 96, 3))
+        img = np.array(img).reshape((1, IMAGE_SIZE, IMAGE_SIZE, 3))
         valence_t.append(labels[i][0])
         arousal_t.append(labels[i][1])
         p = model.predict(img)
@@ -139,24 +143,21 @@ def eval(c_path=None, r_path=None):
         print('CCC'.ljust(20), str(CCC(valence_t, valence_p)).ljust(20), CCC(arousal_t, arousal_p))
 
 if __name__ == '__main__':
-    try:
-        if len(sys.argv) == 3:
-            if sys.argv[1] == '-c':
-                eval(c_path=sys.argv[2])
-            elif sys.argv[1] == '-r':
-                eval(r_path=sys.argv[2])  
-            else:
-                raise Exception()          
-        elif len(sys.argv) == 5:
-            c_path=None
-            r_path=None
-            if sys.argv[1] == '-c':
-                eval(c_path=sys.argv[2], r_path=sys.argv[4])
-            elif sys.argv[1] == '-r':
-                eval(r_path=sys.argv[2], c_path=sys.argv[4])
-            else:
-                raise Exception()
+    if len(sys.argv) == 3:
+        if sys.argv[1] == '-c':
+            eval(c_path=sys.argv[2])
+        elif sys.argv[1] == '-r':
+            eval(r_path=sys.argv[2])  
+        else:
+            raise Exception()          
+    elif len(sys.argv) == 5:
+        c_path=None
+        r_path=None
+        if sys.argv[1] == '-c':
+            eval(c_path=sys.argv[2], r_path=sys.argv[4])
+        elif sys.argv[1] == '-r':
+            eval(r_path=sys.argv[2], c_path=sys.argv[4])
         else:
             raise Exception()
-    except:
-        print('Invalid input, must be -c [path] or -r [path] or both')
+    else:
+        raise Exception()

net.py

@@ -11,14 +11,16 @@ from keras.models import Sequential, load_model, model_from_json
 from keras.optimizers import SGD, Adam
 from keras.preprocessing import image
 from keras.utils.np_utils import to_categorical
+from keras.utils import plot_model
 from sklearn.utils import class_weight
+from keras.applications.mobilenet import DepthwiseConv2D
 
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 CLASSIFY = 0
 REGRESS = 1
 
 # OTPIONS #
-BATCH_SIZE = 250 # VGG: 400     MOB: 250
+BATCH_SIZE = 400 # VGG/ALEX: 400
 EPOCHS = 24
 IMAGE_SIZE = 128
 
@@ -109,46 +111,49 @@ def process_data(C_or_R, paths, labels):
 
 def mobilenet_style_model(C_or_R):
     model = Sequential()
-    # CONV BLOCK 1
-    model.add(SeparableConv2D(32, (3, 3), input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3), padding='same', use_bias=False))
-    model.add(BatchNormalization())
-    model.add(Activation('relu'))
-    model.add(SeparableConv2D(32, (3, 3), strides=(2, 2), padding='same', use_bias=False))
-    model.add(BatchNormalization())
-    model.add(Activation('relu'))
-    model.add(GaussianDropout(0.2))
     # CONV BLOCK 2
-    model.add(SeparableConv2D(64, (3, 3), padding='same', use_bias=False))
+    model.add(DepthwiseConv2D(32, (3, 3), padding='same', use_bias=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
-    model.add(SeparableConv2D(64, (3, 3), strides=(2, 2), padding='same', use_bias=False))
+    model.add(Conv2D(32, (1, 1), strides=(2, 2), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
-    model.add(GaussianDropout(0.2))
-    # CONV BLOCK 3
-    model.add(SeparableConv2D(128, (3, 3), padding='same', use_bias=False))
+    
+    model.add(DepthwiseConv2D(64, (3, 3), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
-    model.add(SeparableConv2D(128, (3, 3), strides=(2, 2), padding='same', use_bias=False))
+    model.add(Conv2D(64, (1, 1), strides=(1, 1), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
-    model.add(GaussianDropout(0.2))
-    # CONV BLOCK 4
-    model.add(SeparableConv2D(256, (3, 3), padding='same', use_bias=False))
+
+    model.add(DepthwiseConv2D(64, (3, 3), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
-    model.add(SeparableConv2D(256, (3, 3), strides=(2, 2), padding='same', use_bias=False))
+    model.add(Conv2D(64, (1, 1), strides=(2, 2), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
-    model.add(GaussianDropout(0.2))
-    # CONV BLOCK 5
-    model.add(SeparableConv2D(512, (3, 3), padding='same', use_bias=False))
+    
+    model.add(DepthwiseConv2D(128, (3, 3), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
-    model.add(SeparableConv2D(512, (3, 3), strides=(2, 2), padding='same', use_bias=False))
+    model.add(Conv2D(128, (1, 1), strides=(1, 1), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
-    model.add(GaussianDropout(0.2))
+    
+    model.add(DepthwiseConv2D(128, (3, 3), padding='same', use_bias=False))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias=False))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    
+    model.add(DepthwiseConv2D(256, (3, 3), padding='same', use_bias=False))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(256, (1, 1), strides=(1, 1), padding='same', use_bias=False))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    
     # FLATTEN
     model.add(GlobalAveragePooling2D())
     # DENSE 1
@@ -243,25 +248,31 @@ def vgg_style_model(C_or_R):
 def alexnet_style_model(C_or_R):
     model = Sequential()
     # CONV BLOCK 1
-    model.add(Conv2D(64, (7, 7), input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3), padding='same', use_bias=False))
+    model.add(Conv2D(16, (9, 9), input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
     model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
     model.add(GaussianDropout(0.2))
     # CONV BLOCK 2
-    model.add(Conv2D(128, (5, 5), padding='same', use_bias=False))
+    model.add(Conv2D(32, (7, 7), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
     model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
     model.add(GaussianDropout(0.2))
     # CONV BLOCK 3
-    model.add(Conv2D(256, (3, 3), padding='same', use_bias=False))
+    model.add(Conv2D(64, (5, 5), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
     model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
     model.add(GaussianDropout(0.2))
     # CONV BLOCK 4
-    model.add(Conv2D(512, (3, 3), padding='same', use_bias=False))
+    model.add(Conv2D(128, (3, 3), padding='same', use_bias=False))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
+    model.add(GaussianDropout(0.2))
+    # CONV BLOCK 5
+    model.add(Conv2D(128, (3, 3), padding='same', use_bias=False))
     model.add(BatchNormalization())
     model.add(Activation('relu'))
     model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
@@ -321,6 +332,8 @@ def load_and_save():
             model.layers.remove(layer)
     model.save('M_VGG/C_T_S.h5')
 
+def visualise(model, name):
+    plot_model(model, to_file=name+'.png', show_shapes=True, show_layer_names=False)
 
 def train(C_or_R, model, name):
     print('** LOADING DATA **')
@@ -364,5 +377,6 @@ if __name__ == '__main__':
     # load_and_save()
     # eval('M_VGG/C_T_S.h5', CLASSIFY)
     # train(CLASSIFY, vgg_style_model(CLASSIFY), 'M_VGG/C')
-    # train(CLASSIFY, alexnet_style_model(CLASSIFY), 'M_ALEX/C')
-    train(CLASSIFY, mobilenet_style_model(CLASSIFY), 'M_MOB/C')
+    train(CLASSIFY, alexnet_style_model(CLASSIFY), 'M_ALEX/C')
+    # train(CLASSIFY, mobilenet_style_model(CLASSIFY), 'M_MOB/C')
+    # visualise(vgg_style_model(CLASSIFY), 'M_VGG/C')