Hello, I found that the result of build-in cross entropy loss with label smoothing is different from my implementation. Not sure if my implementation has some bugs or not. Here is the script:

```
import torch
class label_smooth_loss(torch.nn.Module):
def __init__(self, num_classes, smoothing=0.1):
super(label_smooth_loss, self).__init__()
self.negative = smoothing / (num_classes - 1)
self.positive = (1 - smoothing)
def forward(self, pred, target):
pred = pred.log_softmax(dim=1)
true_dist = torch.zeros_like(pred)
true_dist.fill_(self.negative)
true_dist.scatter_(1, target.data.unsqueeze(1), self.positive)
return torch.sum(-true_dist * pred, dim=1).mean()
x = torch.randn(1,10)
y = torch.randint(10,size=[1])
loss1 = label_smooth_loss(num_classes=10, smoothing=0.1)
loss2 = torch.nn.CrossEntropyLoss(label_smoothing=0.1)
print(loss1(x,y), loss2(x,y))
```