I can not run train because the gradient can not be counted

[qam1314]

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [1, 3, 19, 19, 121]], which is output 0 of AsStridedBackward, is at version 6; expected version 3 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

[JiaweiLian]

Is this problem solved? I got the same problem

[JustWon]

@qam1314 @JiaweiLian Check that you are using pytorch version 1.4.0 as illustrated in requirement.txt. That solved the problem in my case.