【Pytorch】Label Smoothing

理论介绍可以参考 【Inception-v3】《Rethinking the Inception Architecture for Computer Vision》 中的 4.5 Model Regularization via Label Smoothing

本质就是用右边（意会下就行）的标签替换左边的 one-hot 编码形式，让网络别那么愤青，成了二极管（非黑即白）

代码实现如下，来自 【Pytorch】label smoothing

class NMTCritierion(nn.Module):
    """
    1. Add label smoothing
    """
    def __init__(self, label_smoothing=0.0):
        super(NMTCritierion, self).__init__()
        self.label_smoothing = label_smoothing
        self.LogSoftmax = nn.LogSoftmax()

        if label_smoothing > 0:
            self.criterion = nn.KLDivLoss(size_average=False)
        else:
            self.criterion = nn.NLLLoss(size_average=False, ignore_index=100000)
        self.confidence = 1.0 - label_smoothing

    def _smooth_label(self, num_tokens):
        # When label smoothing is turned on,
        # KL-divergence between q_{smoothed ground truth prob.}(w)
        # and p_{prob. computed by model}(w) is minimized.
        # If label smoothing value is set to zero, the loss
        # is equivalent to NLLLoss or CrossEntropyLoss.
        # All non-true labels are uniformly set to low-confidence.
        one_hot = torch.randn(1, num_tokens)
        one_hot.fill_(self.label_smoothing / (num_tokens - 1))
        return one_hot

    def _bottle(self, v):
        return v.view(-1, v.size(2))

    def forward(self, dec_outs, labels):
        scores = self.LogSoftmax(dec_outs)
        num_tokens = scores.size(-1)

        # conduct label_smoothing module
        gtruth = labels.view(-1)
        if self.confidence < 1:
            tdata = gtruth.detach()
            one_hot = self._smooth_label(num_tokens)  # Do label smoothing, shape is [M]
            if labels.is_cuda:
                one_hot = one_hot.cuda()
            tmp_ = one_hot.repeat(gtruth.size(0), 1)  # [N, M]
            tmp_.scatter_(1, tdata.unsqueeze(1), self.confidence)  # after tdata.unsqueeze(1) , tdata shape is [N,1]
            gtruth = tmp_.detach()
        loss = self.criterion(scores, gtruth)
        return loss

使用方式如下：

loss_func = NMTCritierion(0.1) # label smoothing
loss = loss_func(out,label)

其中 out 是网络的输出，label 是输入对应的标签