Pytorch 实现focal_loss 多类别和二分类示例
作者:Kingslayer_ 时间:2021-09-16 17:53:36
我就废话不多说了,直接上代码吧!
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
# 支持多分类和二分类
class FocalLoss(nn.Module):
"""
This is a implementation of Focal Loss with smooth label cross entropy supported which is proposed in
'Focal Loss for Dense Object Detection. (https://arxiv.org/abs/1708.02002)'
Focal_Loss= -1*alpha*(1-pt)^gamma*log(pt)
:param num_class:
:param alpha: (tensor) 3D or 4D the scalar factor for this criterion
:param gamma: (float,double) gamma > 0 reduces the relative loss for well-classified examples (p>0.5) putting more
focus on hard misclassified example
:param smooth: (float,double) smooth value when cross entropy
:param balance_index: (int) balance class index, should be specific when alpha is float
:param size_average: (bool, optional) By default, the losses are averaged over each loss element in the batch.
"""
def __init__(self, num_class, alpha=None, gamma=2, balance_index=-1, smooth=None, size_average=True):
super(FocalLoss, self).__init__()
self.num_class = num_class
self.alpha = alpha
self.gamma = gamma
self.smooth = smooth
self.size_average = size_average
if self.alpha is None:
self.alpha = torch.ones(self.num_class, 1)
elif isinstance(self.alpha, (list, np.ndarray)):
assert len(self.alpha) == self.num_class
self.alpha = torch.FloatTensor(alpha).view(self.num_class, 1)
self.alpha = self.alpha / self.alpha.sum()
elif isinstance(self.alpha, float):
alpha = torch.ones(self.num_class, 1)
alpha = alpha * (1 - self.alpha)
alpha[balance_index] = self.alpha
self.alpha = alpha
else:
raise TypeError('Not support alpha type')
if self.smooth is not None:
if self.smooth < 0 or self.smooth > 1.0:
raise ValueError('smooth value should be in [0,1]')
def forward(self, input, target):
logit = F.softmax(input, dim=1)
if logit.dim() > 2:
# N,C,d1,d2 -> N,C,m (m=d1*d2*...)
logit = logit.view(logit.size(0), logit.size(1), -1)
logit = logit.permute(0, 2, 1).contiguous()
logit = logit.view(-1, logit.size(-1))
target = target.view(-1, 1)
# N = input.size(0)
# alpha = torch.ones(N, self.num_class)
# alpha = alpha * (1 - self.alpha)
# alpha = alpha.scatter_(1, target.long(), self.alpha)
epsilon = 1e-10
alpha = self.alpha
if alpha.device != input.device:
alpha = alpha.to(input.device)
idx = target.cpu().long()
one_hot_key = torch.FloatTensor(target.size(0), self.num_class).zero_()
one_hot_key = one_hot_key.scatter_(1, idx, 1)
if one_hot_key.device != logit.device:
one_hot_key = one_hot_key.to(logit.device)
if self.smooth:
one_hot_key = torch.clamp(
one_hot_key, self.smooth, 1.0 - self.smooth)
pt = (one_hot_key * logit).sum(1) + epsilon
logpt = pt.log()
gamma = self.gamma
alpha = alpha[idx]
loss = -1 * alpha * torch.pow((1 - pt), gamma) * logpt
if self.size_average:
loss = loss.mean()
else:
loss = loss.sum()
return loss
class BCEFocalLoss(torch.nn.Module):
"""
二分类的Focalloss alpha 固定
"""
def __init__(self, gamma=2, alpha=0.25, reduction='elementwise_mean'):
super().__init__()
self.gamma = gamma
self.alpha = alpha
self.reduction = reduction
def forward(self, _input, target):
pt = torch.sigmoid(_input)
alpha = self.alpha
loss = - alpha * (1 - pt) ** self.gamma * target * torch.log(pt) - \
(1 - alpha) * pt ** self.gamma * (1 - target) * torch.log(1 - pt)
if self.reduction == 'elementwise_mean':
loss = torch.mean(loss)
elif self.reduction == 'sum':
loss = torch.sum(loss)
return loss
来源:https://blog.csdn.net/qq_33278884/article/details/91572173
标签:Pytorch,focal,loss,多类别,二分类
![](/images/zang.png)
![](/images/jiucuo.png)
猜你喜欢
做设计还是做产品
2009-06-11 13:01:00
Python实现端口检测的方法
2022-02-01 21:21:02
![](https://img.aspxhome.com/file/2023/0/101720_0s.png)
SQL Server备份和灾难恢复
2010-07-02 12:54:00
![](https://img.aspxhome.com/file/UploadPic/20107/2/01-39s.jpg)
PDO::prepare讲解
2023-06-06 06:15:28
Python基于pillow判断图片完整性的方法
2021-05-12 21:55:50
如何用CocosCreator制作微信小游戏
2023-08-23 16:00:02
![](https://img.aspxhome.com/file/2023/7/56117_0s.png)
MySQL 索引详解
2010-01-20 09:39:00
对Python中for复合语句的使用示例讲解
2023-07-19 17:50:44
分类、属性、关键词与Tag
2009-08-27 12:57:00
CSS图片代码效果汇总
2008-09-04 12:14:00
Python版中国省市经纬度
2021-05-10 20:25:12
php实现mysql备份恢复分卷处理的方法
2023-11-16 20:55:33
caffe的python接口生成配置文件学习
2023-07-09 04:46:41
python批量读取txt文件为DataFrame的方法
2021-09-29 12:04:21
![](https://img.aspxhome.com/file/2023/6/77786_0s.jpg)
asp如何对欲删除的记录确认后再删除?
2009-11-20 18:48:00
python批量修改ssh密码的实现
2023-07-06 13:17:08
python安装dlib库报错问题及解决方法
2023-01-27 16:24:41
asp网站生成静态页面攻略
2007-11-04 15:09:00
基于Python新建用户并产生随机密码过程解析
2021-08-26 11:25:18
Python 文件处理注意事项总结
2022-05-20 23:05:17