我已经训练了两个模型。
第一个模型是UNet:
print(model_unet.summary())__________________________________________________________________________________________________Layer (type) Output Shape Param # Connected to ==================================================================================================input_4 (InputLayer) (None, 128, 128, 1) 0 __________________________________________________________________________________________________conv2d_26 (Conv2D) (None, 128, 128, 32) 320 input_4[0][0] __________________________________________________________________________________________________conv2d_27 (Conv2D) (None, 128, 128, 32) 9248 conv2d_26[0][0] ..........conv2d_44 (Conv2D) (None, 128, 128, 1) 33 zero_padding2d_4[0][0] ==================================================================================================Total params: 7,846,081Trainable params: 7,846,081Non-trainable params: 0第二个是ResNet:
print(model_resnet.summary())__________________________________________________________________________________________________Layer (type) Output Shape Param # Connected to ==================================================================================================input_3 (InputLayer) (None, 128, 128, 3) 0 __________________________________________________________________________________________________conv1_pad (ZeroPadding2D) (None, 134, 134, 3) 0 input_3[0][0] ........conv2d_25 (Conv2D) (None, 128, 128, 3) 99 zero_padding2d_3[0][0] ==================================================================================================Total params: 24,186,915Trainable params: 24,133,795Non-trainable params: 53,120UNet有1个通道（灰度），而ResNet有3个通道。
然后，我试图创建一个集成模型:
def ensemble(models, models_input): outputs = [model(models_input[idx]) for idx, model in enumerate(models)] x = Average()(outputs) model_inputs = [model for model in models_input] model = Model(model_inputs, x) return modelmodels = [model_unet, model_resnet]models_input = [Input((128,128,1)), Input((128,128, 3))]ensemble_model = ensemble(models, models_input)当我尝试在验证数据上进行预测时:
pred_val = ensemble_model.predict(X_val)我收到了以下错误:
Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 2 array(s), but instead got the following list of 1 arrays: [array([[[[0.46755977], [0.52268691], [0.52766109], ....X_val.shape is : (800, 128, 128, 1)我认为问题出在通道上，但我不知道如何解决这个问题。
回答：
如果你的训练数据是灰度图像，并且考虑到你的ResNet模型需要输入RGB图像，那么你应该问自己如何从灰度转换到RGB？一种答案是将灰度图像重复三次以获得RGB图像。然后你可以轻松定义一个模型，带有一个输入层，该层接受你的灰度图像，并相应地将它们输入到你定义的模型中:
from keras import backend as Kinput_image = Input(shape=(128,128,1))unet_out = model_unet(input_image)rgb_image = Lambda(lambda x: K.repeat_elements(x, 3, -1))(input_image)resnet_out = model_resnet(rgb_image)output = Average()([unet_out, resnet_out])ensemble_model = Model(input_image, output)然后你可以轻松地用一个输入数组调用predict:
pred_val = ensemble_model.predict(X_val)这个解决方案的另一种选择是你问题中使用的解决方案。然而，你首先需要将你的图像从灰度转换为RGB，然后将两个数组都传递给predict方法:
X_val_rgb = np.repeat(X_val, 3, -1)pred_val = ensemble_model.predict([X_val, X_val_rgb])