添加到@hkchengrex 的自我回答(用于将来的自我和 API 与 PyTorch 的对等);
可以像这样首先实现functional 版本(在original torch.nn.functional.cross_entropy 中提供一些额外的参数)(我也更喜欢reduction 是callable 而不是预定义的字符串):
import typing
import torch
def bootstrapped_cross_entropy(
inputs,
targets,
iteration,
p: float,
warmup: typing.Union[typing.Callable[[float, int], float], int] = -1,
weight=None,
ignore_index=-100,
reduction: typing.Callable[[torch.Tensor], torch.Tensor] = torch.mean,
):
if not 0 < p < 1:
raise ValueError("p should be in [0, 1] range, got: {}".format(p))
if isinstance(warmup, int):
this_p = 1.0 if iteration < warmup else p
elif callable(warmup):
this_p = warmup(p, iteration)
else:
raise ValueError(
"warmup should be int or callable, got {}".format(type(warmup))
)
# Shortcut
if this_p == 1.0:
return torch.nn.functional.cross_entropy(
inputs, targets, weight, ignore_index=ignore_index, reduction=reduction
)
raw_loss = torch.nn.functional.cross_entropy(
inputs, targets, weight=weight, ignore_index=ignore_index, reduction="none"
).view(-1)
num_pixels = raw_loss.numel()
loss, _ = torch.topk(raw_loss, int(num_pixels * this_p), sorted=False)
return reduction(loss)
还可以将warmup 指定为callable(采用p 和当前iteration)或int,这允许灵活或轻松的调度。
并在每次调用期间自动递增 _WeightedLoss 和 iteration 的类(因此只有 inputs 和 targets 必须通过):
class BoostrappedCrossEntropy(torch.nn.modules.loss._WeightedLoss):
def __init__(
self,
p: float,
warmup: typing.Union[typing.Callable[[float, int], float], int] = -1,
weight=None,
ignore_index=-100,
reduction: typing.Callable[[torch.Tensor], torch.Tensor] = torch.mean,
):
self.p = p
self.warmup = warmup
self.ignore_index = ignore_index
self._current_iteration = -1
super().__init__(weight, size_average=None, reduce=None, reduction=reduction)
def forward(self, inputs, targets):
self._current_iteration += 1
return bootstrapped_cross_entropy(
inputs,
targets,
self._current_iteration,
self.p,
self.warmup,
self.weight,
self.ignore_index,
self.reduction,
)