submodule.py", line 64, in forward out = torch.sum(x*disp,1) my input left and right are (640,480,3)

[Youjiangbaba]

models/submodule.py", line 64, in forward out = torch.sum(x*disp,1) RuntimeError: The size of tensor a (160) must match the size of tensor b (120) at non-singleton dimension 4

Can you tell me what the std-input size is ？or what the img.size need to reshape to？