VGG16 for MRCNN

vgg-16.py

from keras.layers import Conv2D
from keras.layers import MaxPooling2D


"""
VGG16 model
"""
def build_vgg_graph(input_image, stage5=False):

    """
    Model generator

    :param input_image: model input
    :param stage5: enables or disables the last stage
    :return: returns the network stages
    """

    # Stage 1
    x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(input_image)
    x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
    C1 = x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)


    # Stage 2
    x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
    x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
    C2 = x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)

    # Stage 3
    x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
    x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
    x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
    C3 = x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)

    # Stage 4
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
    C4 = x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)

    # Stage 5
    if stage5:
        # Block 5
        x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
        x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
        x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
        C5 = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
    else:
        C5 = None

    return [C1, C2, C3, C4, C5]