通俗理解：
- 一定程度缩小label中min和max的差距
- 可以减小过拟合
for images, labels in train_loader:images, labels = images.cuda(), labels.cuda()N = labels.size(0)# C is the number of classes.smoothed_labels = torch.full(size=(N, C), fill_value=0.1 / (C - 1)).cuda()smoothed_labels.scatter_(dim=1, index=torch.unsqueeze(labels, dim=1), value=0.9)score = model(images)log_prob = torch.nn.functional.log_softmax(score, dim=1)loss = -torch.sum(log_prob * smoothed_labels) / Noptimizer.zero_grad()loss.backward()optimizer.step()
参考：https://www.cnblogs.com/whustczy/p/12520239.html