我有一个Keras模型 =>
输入：灰度图像：(1, 224, 224)
输出：RGB图像：(3, 224, 224)
我想通过输入灰度图像并获得RGB图像来预测像素颜色。我尝试在Keras中构建一个网络，大体上类似于这个（用Tensorflow制作的）网络。
这是模型代码：
first_input = Input(batch_shape=(None, 1, 224, 224))conv0_1_3 = Convolution2D(3, 3, 3, activation='relu', name='conv0_1_3', border_mode='same')(first_input)conv1_1_64 = Convolution2D(64, 3, 3, activation='relu', name='conv1_1', border_mode='same')(conv0_1_3)conv1_2_64 = Convolution2D(64, 3, 3, activation='relu', name='conv1_2', border_mode='same')(conv1_1_64)conv1_2_64 = MaxPooling2D((2, 2))(conv1_2_64)conv2_1_128 = Convolution2D(128, 3, 3, activation='relu', name='conv2_1', border_mode='same')(conv1_2_64)conv2_2_128 = Convolution2D(128, 3, 3, activation='relu', name='conv2_2', border_mode='same')(conv2_1_128)conv2_2_128 = MaxPooling2D((2, 2))(conv2_2_128)conv3_1_256 = Convolution2D(256, 3, 3, activation='relu', name='conv3_1', border_mode='same')(conv2_2_128)conv3_2_256 = Convolution2D(256, 3, 3, activation='relu', name='conv3_2', border_mode='same')(conv3_1_256)conv3_3_256 = Convolution2D(256, 3, 3, activation='relu', name='conv3_3', border_mode='same')(conv3_2_256)conv3_3_256 = MaxPooling2D((2, 2))(conv3_3_256)conv4_1_512 = Convolution2D(512, 3, 3, activation='relu', name='conv4_1', border_mode='same')(conv3_3_256)conv4_2_512 = Convolution2D(512, 3, 3, activation='relu', name='conv4_2', border_mode='same')(conv4_1_512)conv4_3_512 = Convolution2D(512, 3, 3, activation='relu', name='conv4_3', border_mode='same')(conv4_2_512)conv4_3_512 = MaxPooling2D((2, 2))(conv4_3_512)residual1 = BatchNormalization(axis=1, name='batch1')(conv4_3_512)residual1 = Convolution2D(256, 3, 3, activation='relu', name='residual1', border_mode='same')(residual1)residual1 = UpSampling2D(name='upsample1')(residual1)conv3_3_256_batch_norm = BatchNormalization(axis=1, name='batch2')(conv3_3_256)merge1 = merge((conv3_3_256_batch_norm, residual1), mode='concat', name='merge1', concat_axis=0)residual2 = Convolution2D(128, 3, 3, activation='relu', name='residual2', border_mode='same')(merge1)residual2 = UpSampling2D(name='upsample2')(residual2)conv2_2_128_batch_norm = BatchNormalization(axis=1, name='batch3')(conv2_2_128)merge2 = merge((conv2_2_128_batch_norm, residual2), mode='concat', name='merge2', concat_axis=0)residual3 = Convolution2D(64, 3, 3, activation='relu', name='residual3', border_mode='same')(merge2)residual3 = UpSampling2D(name='upsample3')(residual3)conv1_2_64_batch_norm = BatchNormalization(axis=1, name='batch4')(conv1_2_64)merge3 = merge((conv1_2_64_batch_norm, residual3), mode='concat', name='merge3', concat_axis=0)residual4 = Convolution2D(3, 3, 3, activation='relu', name='residual4', border_mode='same')(merge3)residual4 = UpSampling2D(name='upsample4')(residual4)conv0_1_3_batch_norm = BatchNormalization(axis=1, name='batch5')(conv0_1_3)merge4 = merge((conv0_1_3_batch_norm, residual4), mode='concat', name='merge4', concat_axis=0)residual5 = Convolution2D(3, 1, 1, activation='relu', name='residual5', border_mode='same')(merge4)model = Model(input=first_input, output=residual5)这是模型摘要：
Layer (type) Output Shape Param # Connected to ====================================================================================================input_1 (InputLayer) (None, 1, 224, 224) 0 ____________________________________________________________________________________________________conv0_1_3 (Convolution2D) (None, 3, 224, 224) 30 input_1[0][0] ____________________________________________________________________________________________________conv1_1 (Convolution2D) (None, 64, 224, 224) 1792 conv0_1_3[0][0] ____________________________________________________________________________________________________conv1_2 (Convolution2D) (None, 64, 224, 224) 36928 conv1_1[0][0] ____________________________________________________________________________________________________maxpooling2d_1 (MaxPooling2D) (None, 64, 112, 112) 0 conv1_2[0][0] ____________________________________________________________________________________________________conv2_1 (Convolution2D) (None, 128, 112, 112) 73856 maxpooling2d_1[0][0] ____________________________________________________________________________________________________conv2_2 (Convolution2D) (None, 128, 112, 112) 147584 conv2_1[0][0] ____________________________________________________________________________________________________maxpooling2d_2 (MaxPooling2D) (None, 128, 56, 56) 0 conv2_2[0][0] ____________________________________________________________________________________________________conv3_1 (Convolution2D) (None, 256, 56, 56) 295168 maxpooling2d_2[0][0] ____________________________________________________________________________________________________conv3_2 (Convolution2D) (None, 256, 56, 56) 590080 conv3_1[0][0] ____________________________________________________________________________________________________conv3_3 (Convolution2D) (None, 256, 56, 56) 590080 conv3_2[0][0] ____________________________________________________________________________________________________maxpooling2d_3 (MaxPooling2D) (None, 256, 28, 28) 0 conv3_3[0][0] ____________________________________________________________________________________________________conv4_1 (Convolution2D) (None, 512, 28, 28) 1180160 maxpooling2d_3[0][0] ____________________________________________________________________________________________________conv4_2 (Convolution2D) (None, 512, 28, 28) 2359808 conv4_1[0][0] ____________________________________________________________________________________________________conv4_3 (Convolution2D) (None, 512, 28, 28) 2359808 conv4_2[0][0] ____________________________________________________________________________________________________maxpooling2d_4 (MaxPooling2D) (None, 512, 14, 14) 0 conv4_3[0][0] ____________________________________________________________________________________________________batch1 (BatchNormalization) (None, 512, 14, 14) 1024 maxpooling2d_4[0][0] ____________________________________________________________________________________________________residual1 (Convolution2D) (None, 256, 14, 14) 1179904 batch1[0][0] ____________________________________________________________________________________________________upsample1 (UpSampling2D) (None, 256, 28, 28) 0 residual1[0][0] ____________________________________________________________________________________________________batch2 (BatchNormalization) (None, 256, 28, 28) 512 conv3_3[0][0] ____________________________________________________________________________________________________merge1 (Merge) (None, 512, 28, 28) 0 batch2[0][0] upsample1[0][0] ____________________________________________________________________________________________________residual2 (Convolution2D) (None, 128, 28, 28) 589952 merge1[0][0] ____________________________________________________________________________________________________upsample2 (UpSampling2D) (None, 128, 56, 56) 0 residual2[0][0] ____________________________________________________________________________________________________batch3 (BatchNormalization) (None, 128, 56, 56) 256 conv2_2[0][0] ____________________________________________________________________________________________________merge2 (Merge) (None, 256, 56, 56) 0 batch3[0][0] upsample2[0][0] ____________________________________________________________________________________________________residual3 (Convolution2D) (None, 64, 56, 56) 147520 merge2[0][0] ____________________________________________________________________________________________________upsample3 (UpSampling2D) (None, 64, 112, 112) 0 residual3[0][0] ____________________________________________________________________________________________________batch4 (BatchNormalization) (None, 64, 112, 112) 128 conv1_2[0][0] ____________________________________________________________________________________________________merge3 (Merge) (None, 128, 112, 112) 0 batch4[0][0] upsample3[0][0] ____________________________________________________________________________________________________residual4 (Convolution2D) (None, 3, 112, 112) 3687 merge3[0][0] ____________________________________________________________________________________________________upsample4 (UpSampling2D) (None, 3, 224, 224) 0 residual4[0][0] ____________________________________________________________________________________________________batch5 (BatchNormalization) (None, 3, 224, 224) 6 conv0_1_3[0][0] ____________________________________________________________________________________________________merge4 (Merge) (None, 6, 224, 224) 0 batch5[0][0] upsample4[0][0] ____________________________________________________________________________________________________residual5 (Convolution2D) (None, 3, 224, 224) 21 merge4[0][0] ====================================================================================================Total params: 9,164,694回答：
