Source code for torch.nn.utils.clip_grad

import warnings
import torch
from torch._six import inf
from typing import Union, Iterable

_tensor_or_tensors = Union[torch.Tensor, Iterable[torch.Tensor]]


def clip_grad_norm_(
        parameters: _tensor_or_tensors, max_norm: float, norm_type: float = 2.0,
        error_if_nonfinite: bool = False) -> torch.Tensor:
    r"""Clips gradient norm of an iterable of parameters.

    The norm is computed over all gradients together, as if they were
    concatenated into a single vector. Gradients are modified in-place.

    Args:
        parameters (Iterable[Tensor] or Tensor): an iterable of Tensors or a
            single Tensor that will have gradients normalized
        max_norm (float or int): max norm of the gradients
        norm_type (float or int): type of the used p-norm. Can be ``'inf'`` for
            infinity norm.
        error_if_nonfinite (bool): if True, an error is thrown if the total
            norm of the gradients from :attr:``parameters`` is ``nan``,
            ``inf``, or ``-inf``. Default: False (will switch to True in the future)

    Returns:
        Total norm of the parameters (viewed as a single vector).
    """
    if isinstance(parameters, torch.Tensor):
        parameters = [parameters]
    parameters = [p for p in parameters if p.grad is not None]
    max_norm = float(max_norm)
    norm_type = float(norm_type)
    if len(parameters) == 0:
        return torch.tensor(0.)
    device = parameters[0].grad.device
    if norm_type == inf:
        norms = [p.grad.detach().abs().max().to(device) for p in parameters]
        total_norm = norms[0] if len(norms) == 1 else torch.max(torch.stack(norms))
    else:
        total_norm = torch.norm(torch.stack([torch.norm(p.grad.detach(), norm_type).to(device) for p in parameters]), norm_type)
    if error_if_nonfinite and torch.logical_or(total_norm.isnan(), total_norm.isinf()):
        raise RuntimeError(
            f'The total norm of order {norm_type} for gradients from '
            '`parameters` is non-finite, so it cannot be clipped. To disable '
            'this error and scale the gradients by the non-finite norm anyway, '
            'set `error_if_nonfinite=False`')
    clip_coef = max_norm / (total_norm + 1e-6)
    # Note: multiplying by the clamped coef is redundant when the coef is clamped to 1, but doing so
    # avoids a `if clip_coef < 1:` conditional which can require a CPU <=> device synchronization
    # when the gradients do not reside in CPU memory.
    clip_coef_clamped = torch.clamp(clip_coef, max=1.0)
    for p in parameters:
        p.grad.detach().mul_(clip_coef_clamped.to(p.grad.device))
    return total_norm


def clip_grad_norm(
        parameters: _tensor_or_tensors, max_norm: float, norm_type: float = 2.,
        error_if_nonfinite: bool = False) -> torch.Tensor:
    r"""Clips gradient norm of an iterable of parameters.

    .. warning::
        This method is now deprecated in favor of
        :func:`torch.nn.utils.clip_grad_norm_`.
    """
    warnings.warn("torch.nn.utils.clip_grad_norm is now deprecated in favor "
                  "of torch.nn.utils.clip_grad_norm_.", stacklevel=2)
    return clip_grad_norm_(parameters, max_norm, norm_type, error_if_nonfinite)


def clip_grad_value_(parameters: _tensor_or_tensors, clip_value: float) -> None:
    r"""Clips gradient of an iterable of parameters at specified value.

    Gradients are modified in-place.

    Args:
        parameters (Iterable[Tensor] or Tensor): an iterable of Tensors or a
            single Tensor that will have gradients normalized
        clip_value (float or int): maximum allowed value of the gradients.
            The gradients are clipped in the range
            :math:`\left[\text{-clip\_value}, \text{clip\_value}\right]`
    """
    if isinstance(parameters, torch.Tensor):
        parameters = [parameters]
    clip_value = float(clip_value)
    for p in filter(lambda p: p.grad is not None, parameters):
        p.grad.data.clamp_(min=-clip_value, max=clip_value)