梯度裁剪的作用
防止梯度爆炸。对网络所有参数求范数,和最大梯度阈值相比,如果clip_coef<1,范数大于阈值,则所有梯度值乘以系数。
pytorch对应代码
torch.nn.utils.clip_grad_norm_(parameters, max_norm, norm_type=2)
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