RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

[Krb686]

Running this code with pytorch >= 1.5 gives the following error

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor            
[3, 64, 7, 7]] is at version 3; 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).

See this issue

According to albanD the issue is the discriminator parameters being updated in place but also being needed afterwards.

The error happens here. I'm not familiar enough with GANs yet to know what to fix here.