focal_loss.py

import torch
import torch.nn as nn
from torch.autograd import Variable

class FocalLoss(nn.Module):
    
    def __init__(self, class_num=5, alpha=None, gamma=2, size_average=True):
        super(FocalLoss, self).__init__()
        if alpha is None:
            self.alpha = Variable(torch.ones(class_num, 1))
        else:
            if isinstance(alpha, Variable):
                self.alpha = alpha
            else:
                self.alpha = Variable(alpha)
        self.gamma = gamma
        self.class_num = class_num
        self.size_average = size_average

    def forward(self, inputs, targets):
        N = inputs.size(0)
        C = inputs.size(1)
        P = F.softmax(inputs)

        class_mask = inputs.data.new(N, C).fill_(0)
        class_mask = Variable(class_mask)
        ids = targets.view(-1, 1)
        class_mask.scatter_(1, ids.data, 1.)
        #print(class_mask)


        if inputs.is_cuda and not self.alpha.is_cuda:
            self.alpha = self.alpha.cuda()
        alpha = self.alpha[ids.data.view(-1)]

        probs = (P*class_mask).sum(1).view(-1,1)

        log_p = probs.log()
        #print('probs size= {}'.format(probs.size()))
        #print(probs)

        batch_loss = -alpha*(torch.pow((1-probs), self.gamma))*log_p 
        #print('-----bacth_loss------')
        #print(batch_loss)


        if self.size_average:
            loss = batch_loss.mean()
        else:
            loss = batch_loss.sum()
        return loss


class FocalLoss_(nn.Module):
    def __init__(self, alpha=1, gamma=2, logits=False, reduce=True):
        super(FocalLoss, self).__init__()
        self.alpha = alpha
        self.gamma = gamma
        self.logits = logits
        self.reduce = reduce

    def forward(self, inputs, targets):
        inputs = torch.sigmoid(inputs)
        if self.logits:
            BCE_loss = F.binary_cross_entropy_with_logits(inputs, targets)
        else:
            BCE_loss = F.binary_cross_entropy(inputs, targets)
            #BCE_loss = torch.nn.BCEWithLogitsLoss(inputs, targets)

        pt = torch.exp(-BCE_loss)
        F_loss = self.alpha * (1-pt)**self.gamma * BCE_loss

        if self.reduce:
            return torch.mean(F_loss)
        else:
            return F_loss