add steph model + vgg19 avec initialisation glorot

skluc/main/tensorflow_/models.py

@@ -14,6 +14,21 @@ def build_lenet_model(input_shape):
     model.add(Flatten())
     return model
 
+def build_steph_model(input_shape):
+    model = Sequential()
+    model.add(Conv2D(64, kernel_size=(4, 4), strides=(2, 2), padding='same', activation=None, input_shape=input_shape))
+    model.add(Activation('relu'))
+    model.add(Conv2D(128, kernel_size=(4, 4), strides=(2, 2), padding='same', activation=None))
+    model.add(Activation('relu'))
+    model.add(Conv2D(256, kernel_size=(4, 4), strides=(2, 2), padding='same', activation=None))
+    model.add(Activation('relu'))
+    model.add(Conv2D(512, kernel_size=(3, 3), strides=(1, 1), padding='same', activation=None))
+    model.add(BatchNormalization())
+    model.add(MaxPooling2D((2, 2)))
+    model.add(Activation('relu'))
+    model.add(Flatten())
+    return model
+
 
 def build_vgg19_model(input_shape, weight_decay=0.0001):
     model = Sequential()
@@ -100,3 +115,90 @@ def build_vgg19_model(input_shape, weight_decay=0.0001):
     model.add(Flatten(name='flatten'))
 
     return model
+
+
+def build_vgg19_model_glorot(input_shape, weight_decay=0.0001):
+    model = Sequential()
+
+    # Block 1
+    model.add(Conv2D(64, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block1_conv1', input_shape=input_shape))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(64, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block1_conv2'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool'))
+
+    # Block 2
+    model.add(Conv2D(128, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block2_conv1'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(128, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block2_conv2'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool'))
+
+    # Block 3
+    model.add(Conv2D(256, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block3_conv1'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(256, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block3_conv2'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(256, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block3_conv3'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(256, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block3_conv4'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool'))
+
+    # Block 4
+    model.add(Conv2D(512, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block4_conv1'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(512, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block4_conv2'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(512, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block4_conv3'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(512, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block4_conv4'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool'))
+
+    # Block 5
+    model.add(Conv2D(512, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block5_conv1'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(512, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block5_conv2'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(512, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block5_conv3'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(Conv2D(512, (3, 3), padding='same', kernel_regularizer=l2(weight_decay),
+                     name='block5_conv4'))
+    model.add(BatchNormalization())
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool'))
+
+    model.add(Flatten(name='flatten'))
+
+    return model
\ No newline at end of file