Question

我训练了2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: 7,846,081
Trainable params: 7,846,081
Non-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: 24,186,915
Trainable params: 24,133,795
Non-trainable params: 53,120

UNet有1个通道（灰色），ResNet有3个通道。

然后，我正在尝试创建一个集成模型：

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 model

models = [model_unet, model_resnet]
models_input = [Input((128,128,1)), Input((128,128, 3))]

ensemble_model = ensemble(models, models_input)

当我尝试预测验证数据时：

pred_val = ensemble_model.predict(X_val)

我收到错误：

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)

我认为问题是渠道，但我不知道该如何克服。

Answer 1

如果您的训练数据是灰度图像，并且考虑到ResNet模型将RGB图像作为输入RGB图像，那么您应该问自己：如何将灰度图像转换为RGB？一个答案是将灰度图像重复3次以获得RBG图像。然后，您可以轻松地使用一个输入层定义一个模型，该模型将获取灰度图像并将其相应地馈送到您定义的模型中：

from keras import backend as K

input_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，您可以使用一个输入数组轻松调用predict：

pred_val = ensemble_model.predict(X_val)

该解决方案的一种替代方法是使用您在问题中使用的解决方案。但是，您首先需要将图像从灰度转换为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])

具有不同输入的集成模型（预计查看2个数组）

1 个答案: