我已经训练了 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 channel (灰色),ResNet 有 3 个 channel 。
然后,我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)
我认为问题出在 channel 上,但我不知道如何克服这个问题。
最佳答案
如果你的训练数据是灰度图像,并且考虑到你的 ResNet 模型将 RGB 图像作为输入,那么你应该问自己,你想如何从灰度到 RGB?一种答案是重复灰度图像 3 次以获得 RBG 图像。然后,您可以轻松地定义一个具有一个输入层的模型,该输入层获取灰度图像并将其相应地输入到您定义的模型中:
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预测
:
pred_val = ensemble_model.predict(X_val)
此解决方案的一种替代方案是采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])
关于python - 具有不同输入的集成模型(预计会看到 2 个数组),我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/52634226/