【RuntimeError】the derivative for 'target' is not implemented

报错信息：
Traceback (most recent call last):  
  File "/users/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "/users/anaconda3/lib/python3.6/site-packages/torch/nn/modules/loss.py", line 504, in forward
    return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction)
  File "/users4/zsun/anaconda3/lib/python3.6/site-packages/torch/nn/functional.py", line 2027, in binary_cross_entropy
    input, target, weight, reduction_enum)
RuntimeError: the derivative for 'target' is not implemented

出错代码为：

torch.nn.BCELoss(preds, targets)

错误为：

loss函数的target，即第二项targets的导数不应该有梯度

查错误：

print(preds.requires_grad，targets.requires_grad)；

发现结果为True，True

然而loss函数的preds.requires_grad=True，targets.requires_grad应该为False

改正：

加入一行targets = targets.detach()

NOTE：

targets.requires_grad = False不可以

原因是：

you can only change requires_grad flags of leaf variables.

If you want to use a computed variable in a subgraph that doesn't require differentiation please use detach()