CV常见损失函数

原创

已于 2022-04-20 15:26:17 修改 · 565 阅读

收录于

当前文章被以下社区和专栏收录：

于 2022-04-20 11:23:26 首次发布

本文介绍了Dice Loss损失函数，它在衡量两张热力图之间的多样性时引入了IoU概念。同时，Focal Loss被详细解释为一种针对分类问题的注意力机制，通过调整易样本和难样本的权重。两者在计算机视觉任务中都关注样本不平衡问题的解决策略。

Dice loss

class DiceLoss(nn.Module):
    '''
    Loss function from https://arxiv.org/abs/1707.03237,
    where iou computation is introduced heatmap manner to measure the
    diversity bwtween tow heatmaps.
    '''
    def __init__(self, eps=1e-6):
        super(DiceLoss, self).__init__()
        self.eps = eps

    def forward(self, pred: torch.Tensor, gt, mask, weights=None):
        '''
        pred: one or two heatmaps of shape (N, 1, H, W),
            the losses of tow heatmaps are added together.
        gt: (N, 1, H, W)
        mask: (N, H, W)
        '''
        assert pred.dim() == 4, pred.dim()
        return self._compute(pred, gt, mask, weights)

    def _compute(self, pred, gt, mask, weights):
        if pred.dim()