You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank u, but I get some new troubles when I train this code directly. It occur 'RuntimeError('cuda runtime error (77) : an illegal memory access was encountered '. So I add 'torch.cuda.set_device(1)' on the top, but here's a new one 'RuntimeError('cuda runtime error (4) : unspecified launch failure at ' These all happen at batch_losses.append(loss_value) in train.py. I try to skip it and sth correspond to it, but the same thing happens in loss.backward(). Could you give me some advice?
I don't find the weight file 'class_weights.pkl',can you tell me have to get it
The text was updated successfully, but these errors were encountered: