Ishant Thakare

Results 3 comments of Ishant Thakare

Here is my analysis on the issue: **Issue Reproduction:** - Using SGD as an optimizer in PyTorch_TinyImageNet Tutorial optimizer_SGD = optim.SGD(model.parameters(), lr=1e-1) - This issue is observed when we use...

Yes, for now we can fix this by giving a non-zero value to momentum