SRResNet_simple.py 文件源码

def create_model(img_height,img_width,img_channel):
    ip = Input(shape=(img_height, img_width,img_channel))
    L_1 = Conv2D(64, (9, 9), padding='same', activation='linear', kernel_initializer='glorot_uniform')(ip)
    L_1 = LeakyReLU(alpha=0.25)(L_1)
    L_2=L_1
    for i in range(3):
        L_2 = residual_block(L_2, 64,3)

    L_3 = Conv2D(64, (3, 3), padding='same',kernel_initializer='glorot_uniform')(L_2)
    L_3 = BatchNormalization(axis=-1)(L_3)
    L_3 = add([L_1,L_3])
    L_4= Conv2D(128, (1, 1), padding='same',kernel_initializer='glorot_uniform')(L_3)
    op = Conv2D(img_channel, (9, 9),padding='same', activation='tanh', kernel_initializer='glorot_uniform')(L_4)

    deblocking =Model(inputs=ip,outputs= op)
    optimizer = optimizers.Adam(lr=1e-4)
    deblocking.compile(optimizer=optimizer,loss='mean_squared_error', metrics=[psnr,ssim])
    return deblocking