RuntimeError: One of the differentiated Tensors appears to not have been used in the graph. Set allow_unused=True if this is the desired behavior.

[yzakzero]

Hi, thank you very much for your work.
When I use my own dataset and model, It error in this Line:
pseudo_grads = torch.autograd. grad(pseudo_loss, pseudo_net.parameters(), create_graph=True)

The following error message is displayed:

RuntimeError: One of the differentiated Tensors appears to not have been used in the graph. Set allow_unused=True if this is the desired behavior.

Looking forward to your reply.

[machineNo6]

I meet the same problem, do you deal with it?

[yzakzero]

谢谢，收到！