Closed Ericmututu closed 1 year ago
Hi, thanks for asking. I clarify that we have updated our codebase, did you try with our up-to-date codebase in main branch? I have run it in my machine, and everything works well. Also, it seems that your mentioned issues were resolved by us before.
Since it is a clarification thing, and if there are no other questions, I will close this issue.
When implementing the
run_fsc.py
inexamples\few-shot-classification\
following the direction of usages directly, I meet the errorRuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper__index_select)
. It seems that the model is on the GPU while the data on CPU. How do I fix it?Thanks in advance!