lirongwu / psc-cpi Goto Github PK

Hello，When I run the line loss.backward(), I get an error:

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [32, 1000, 256]], which is output 0 of ReluBackward0, is at version 1; expected version 0 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!

The first time I encounter this error, it seems that the error message is caused by the relu function.I really don't know how to solve this problem, due to server graphics card issues, I can not use Torch 1.6.0, must choose a higher cuda version (Torch 1.13.0), I don't know if this is the reason. I am looking forward to your reply and hope to get your help