RuntimeError: input is not contiguous

When i reshape a tensor (if the rank is changed), i get the following error. x = ... # Tensor of shape (100, 20) x.view(-1) # expect a tensor of shape (2000) RuntimeError: input is not contiguous What does ‘contiguous’ mean and why does this error occur? It means that your tensor is not a single block of memory, but a block with holes. view can be only used with contiguous tensors, so if you need

[kent-where-the-light-is]

“A classical way to obtain this bug is to use transposition. If you do x = torch.Tensor(5,2) y = x.t()”