VGG16_Keras.py

def VGG16(weights_path=None):
    model = Sequential()
    model.add(ZeroPadding2D((1,1),input_shape=(224,224,3)))
    
    model.add(Convolution2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1'))
    model.add(Convolution2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2'))
    model.add(MaxPooling2D((2,2), strides=(2,2), name='block1_pool'))

    model.add(Convolution2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1'))
    model.add(Convolution2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2'))
    model.add(MaxPooling2D((2,2), strides=(2,2), name='block2_pool'))

    model.add(Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1'))
    model.add(Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2'))
    model.add(Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3'))
    model.add(MaxPooling2D((2,2), strides=(2,2), name='block3_pool'))

    model.add(Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1'))
    model.add(Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2'))
    model.add(Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3'))
    model.add(MaxPooling2D((2,2), strides=(2,2), name='block4_pool'))

    model.add(Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1'))
    model.add(Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2'))
    model.add(Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3'))
    model.add(MaxPooling2D((2,2), strides=(2,2), name='block5_pool'))

    model.add(Flatten(name='flatten'))
    model.add(Dense(4096, activation='relu', name='fully_connected_1'))
    model.add(Dropout(0.5))
    model.add(Dense(4096, activation='relu', name='fully_connected_2'))
    model.add(Dropout(0.5))
    model.add(Dense(1000, activation='softmax', name='predictions'))   
    
    if weights_path:
        model.load_weights(weights_path)
    
    return model