Nishikanta
Nishikanta
> @sh7jacobi Thank you for your answer. After further investigation, it seems that torch.backends.cudnn.benchmark = True did the trick :) Apparently it 'optimizes' CuDNN somehow, don't really understand how thought....
@BlueBlaze6335 plz assign me
plz assign me
@BlueBlaze6335 plz assign me
@BlueBlaze6335 plz assign me
plz assign me to add cezan 256