keras_cnn.py 文件源码

def baseline_model():
    # create model
    input_shape = (1, 50, 50)
    model = Sequential()
    model.add(Conv2D(16, (3, 3),
                 activation='sigmoid',
                 strides=(1, 1),
                 data_format='channels_first',
                 padding='same',
                 input_shape=input_shape))
    model.add(MaxPooling2D(pool_size=(2, 2), data_format='channels_first'))
    model.add(Conv2D(48, kernel_size=(3, 3),
                 activation='sigmoid',
                 strides=(1, 1),
                 data_format="channels_first",
                 padding="same",
                 input_shape=input_shape))
    model.add(Conv2D(64, kernel_size=(3, 3),
                 activation='sigmoid',
                 strides=(1, 1),
                 data_format="channels_first",
                 padding="same",
                 input_shape=input_shape))
    model.add(MaxPooling2D(pool_size=(2, 2), data_format='channels_first'))
    model.add(Conv2D(64, kernel_size=(3, 3),
                 activation='sigmoid',
                 strides=(1, 1),
                 data_format="channels_first",
                 padding="same",
                 input_shape=input_shape))
    model.add(Flatten())
    model.add(Dense(64, activation='sigmoid'))
    model.add(Dense(68*2, activation='tanh'))
    # Compile model
    sgd = SGD(lr=1e-4, momentum=0.9, decay=1e-6, nesterov=False)
    model.compile(loss='mean_squared_error', optimizer=sgd)
    return model