model.py 文件源码

def get_frontend(input_width, input_height) -> Sequential:
    model = Sequential()
    # model.add(ZeroPadding2D((1, 1), input_shape=(input_width, input_height, 3)))
    model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1', input_shape=(input_width, input_height, 3)))
    model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))

    model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_1'))
    model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_2'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))

    model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_1'))
    model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_2'))
    model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_3'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))

    model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_1'))
    model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_2'))
    model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_3'))

    # Compared to the original VGG16, we skip the next 2 MaxPool layers,
    # and go ahead with dilated convolutional layers instead

    model.add(AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_1'))
    model.add(AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_2'))
    model.add(AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_3'))

    # Compared to the VGG16, we replace the FC layer with a convolution

    model.add(AtrousConvolution2D(4096, 7, 7, atrous_rate=(4, 4), activation='relu', name='fc6'))
    model.add(Dropout(0.5))
    model.add(Convolution2D(4096, 1, 1, activation='relu', name='fc7'))
    model.add(Dropout(0.5))
    # Note: this layer has linear activations, not ReLU
    model.add(Convolution2D(21, 1, 1, activation='linear', name='fc-final'))

    # model.layers[-1].output_shape == (None, 16, 16, 21)
    return model