loss2.backward():runtime error

[MindsetFather]

Thanks for the open source code! And there is a problem confuing me.
When i running the code with [python main.py],there is a Pytorch error:
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [512, 38]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

Code error is located in solver.py,line 188
//Minimax strategy
loss1.backward(retain_graph=True)
self.optimizer.step()
loss2.backward()
self.optimizer.step()

when i change the code to
loss1.backward(retain_graph=True)
//self.optimizer.step()
loss2.backward()
self.optimizer.step()

It worked!
I wonder if the first [self.optimizer.step()] should be annotated,if not, how to resolve the error.
Thank you.

[wuhaixu2016]

Hi, I think both versions are fine.

But, to solve the error that you come across at first (keep the first backward), you should change the pytorch version as 1.4.0

[MindsetFather]

thank you ,it worked