invalid variables

[vkadykova]

When I run cifar.py I have the error:
new() received an invalid combination of arguments - got (Tensor, int, int, int), but expected one of:

• (torch.device device)
• (tuple of ints size, torch.device device)
• (torch.Storage storage)
• (Tensor other)
• (object data, torch.device device)
  What is the problem?
  Thanks for the answer!

[bupt-zsp]

I meet the same problem, did you solve it now?

[vkadykova]

Still no. Write, please, if you solve it:)

[bupt-zsp]

It's a version problem, I can run it in pytorch 0.2.0.

[szagoruyko]

thats due to torch.IntTensor becoming a variable, so creating a new tensor with shape from torch.IntTensor is not possible without explicit cast to int now. going to update the code for PyTorch 0.4 now

[szagoruyko]

fixed by #21

[vkadykova]

Thanks a lot!