Pytorch 中 expand, expand_as是共享内存的，只是原始数据的一个视图 view

mask = mask_miss.expand_as(sxing).clone()            # type: torch.Tensor
mask[:, :, -2, :, :] = 1   # except for person mask channel

为了避免对expand后对某个channel操作会影响原始tensor的全部元素，需要使用clone()

如果没有clone()，对mask_miss的某个通道赋值后，所有通道上的tensor都会变成1！

 

# Notice! expand does not allocate more memory but just make the tensor look as if you expanded it.
# You should call .clone() on the resulting tensor if you plan on modifying it
# https://discuss.pytorch.org/t/very-strange-behavior-change-one-element-of-a-tensor-will-influence-all-elements/41190