for people trying to just get an answer quickly:
torch.nn.utils.clip_grad_norm(mdl_sgd.parameters(),clip)
or with in-place clamp:
W.grad.data.clamp_(-clip,clip)
also similar Q:
for people trying to just get an answer quickly:
torch.nn.utils.clip_grad_norm(mdl_sgd.parameters(),clip)
or with in-place clamp:
W.grad.data.clamp_(-clip,clip)
also similar Q: