class FocalLoss(nn.Module):
# Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
super(FocalLoss, self).__init__()
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
self.gamma = gamma
self.alpha = alpha
self.reduction = loss_fcn.reduction
self.loss_fcn.reduction = 'none' # required to apply FL to each element
def forward(self, pred, true):
loss = self.loss_fcn(pred, true)
# p_t = torch.exp(-loss)
# loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability
# TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
pred_prob = torch.sigmoid(pred) # prob from logits
p_t = true * pred_prob + (1 - true) * (1 - pred_prob)
alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
modulating_factor = (1.0 - p_t) ** self.gamma
loss *= alpha_factor * modulating_factor
if self.reduction == 'mean':
return loss.mean()
elif self.reduction == 'sum':
return loss.sum()
else: # 'none'
return loss
多分类:
# -*- coding: utf-8 -*-
"""
Created on 18-6-7 上午10:11
@author: ronghuaiyang
"""
import torch
import torch.nn as nn
class FocalLoss(nn.Module):
def __init__(self, gamma=0, eps=1e-7):
super(FocalLoss, self).__init__()
self.gamma = gamma
self.eps = eps
self.ce = torch.nn.CrossEntropyLoss()
def forward(self, input, target):
logp = self.ce(input, target)
p = torch.exp(-logp)
loss = (1 - p) ** self.gamma * logp
return loss.mean()
抑制简单样本让模型更关注困难样本的学习