torch.nn.utils.clip_grad_norm¶
- torch.nn.utils.clip_grad_norm(parameters, max_norm, norm_type=2.0, error_if_nonfinite=False, foreach=None)[source][source]¶
Clip the gradient norm of an iterable of parameters.
Warning
This method is now deprecated in favor of
torch.nn.utils.clip_grad_norm_().- Return type
