用法
參數列表
- parameters 一個由張量或單個張量組成的可迭代對象(模型參數)
- max_norm 梯度的最大范數
- nort_type 所使用的范數類型。默認為L2范數,可以是無窮大范數inf
設parameters里所有參數的梯度的范數為total_norm,
若max_norm>total_norm,parameters里面的參數的梯度不做改變;
若max_norm<total_norm,parameters里面的參數的梯度都要乘以一個系數clip_coef
官方代碼
def clip_grad_norm_(parameters, max_norm, norm_type=2):
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.
Arguments:
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.
Returns:
Total norm of the parameters (viewed as a single vector).
"""
if isinstance(parameters, torch.Tensor):
parameters = [parameters]
#第一步
parameters = list(filter(lambda p: p.grad is not None, parameters))
max_norm = float(max_norm)
norm_type = float(norm_type)
if norm_type == inf:
total_norm = max(p.grad.data.abs().max() for p in parameters)
else:
total_norm = 0
for p in parameters:
#第二步
param_norm = p.grad.data.norm(norm_type)
#第三步
total_norm += param_norm.item() ** norm_type
total_norm = total_norm ** (1. / norm_type)
clip_coef = max_norm / (total_norm + 1e-6)
if clip_coef < 1:
for p in parameters:
p.grad.data.mul_(clip_coef)
return total_norm
意義
這個函數的主要目的是對parameters里的所有參數的梯度進行規范化
梯度裁剪解決的是梯度消失或爆炸的問題,即設定閾值,如果梯度超過閾值,那么就截斷,將梯度變為閾值
