基于我提出的其他一些问题，我试图定义一个自定义丢失函数，它允许我使用另一个张量的内容对输入张量的内容进行切片：
We are sorry, but you do not have access to this service.
我收到以下错误：
def innerLoss(z):
y_pred = z[0]
patch_x = z[1][0]
patch_y = z[1][1]
patch_true = y_pred[patch_y:patch_y+10, patch_x:patch_x+10, 0]
return 0
originalInputs = Input(shape=(128, 128, 1))
featureInputs = Input(shape=(2,), dtype="int64")
originalOutputs = Input(shape=(128, 128, 1))
loss = Lambda(innerLoss)([originalOutputs, featureInputs])
outerModel = Model(inputs=[originalInputs, featureInputs], outputs=loss)
此处，ValueError: Shapes must be equal rank, but are 1 and 0
From merging shape 1 with other shapes. for 'lambda_3/strided_slice_2/stack_1' (op: 'Pack') with input shapes: [2], [2], [].
将包含一对坐标，告诉我们在featureInputs中开始切割图片的位置。