W3cubDocs

/PyTorch 2.9

torch.nn.utils.clip_grad.clip_grad_norm

torch.nn.utils.clip_grad.clip_grad_norm(parameters, max_norm, norm_type=2.0, error_if_nonfinite=False, foreach=None) [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

Tensor

© 2025, PyTorch Contributors
PyTorch has a BSD-style license, as found in the LICENSE file.
https://docs.pytorch.org/docs/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm.html