No, loss.backward()
calculates the gradient, clip_grad_norm_
limits it’s norm and optimizer.step()
updates the parameters. But yes, you need the first and last.
Best regards
Thomas
No, loss.backward()
calculates the gradient, clip_grad_norm_
limits it’s norm and optimizer.step()
updates the parameters. But yes, you need the first and last.
Best regards
Thomas
Does Variable.grad.data gives access to normalized gradients per batch? If yes, how can I have access to unnormalized gradients?