RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
After some preliminary investigation, the problem seems to be this line. It ignores the self.args.cuda parameter and decides whether to put the z mask purely based on where CUDA is available.
I got this error when trying to run the Introspective Rationale Explainer Sample Notebook:
After some preliminary investigation, the problem seems to be this line. It ignores the
self.args.cuda
parameter and decides whether to put thez
mask purely based on where CUDA is available.