[Pytorch]RuntimeError: cuda runtime error (59) : device-side assert triggered at /pytorch/aten/src/THC/generic/THCTensorMath.cu:26

使用Pytorch进行训练的时候，会出现：

THCudaCheck FAIL file=/pytorch/aten/src/THC/generic/THCTensorMath.cu line=26 error=59 : device-side assert triggered
/pytorch/aten/src/THCUNN/ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int, int, long) [with Dtype = float, Acctype = float]: block: [0,0,0], thread: [1,0,0] Assertion `t >= 0 && t < n_classes` failed.
/pytorch/aten/src/THCUNN/ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int, int, long) [with Dtype = float, Acctype = float]: block: [0,0,0], thread: [6,0,0] Assertion `t >= 0 && t < n_classes` failed.
/pytorch/aten/src/THCUNN/ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int, int, long) [with Dtype = float, Acctype = float]: block: [0,0,0], thread: [7,0,0] Assertion `t >= 0 && t < n_classes` failed.
Traceback (most recent call last):
  File "/home/ubuntu/bigdisk/part1/Gabor_CNN/demo/RS19.py", line 163, in <module>
    train(epoch+1)
  File "/home/ubuntu/bigdisk/part1/Gabor_CNN/demo/RS19.py", line 133, in train
    loss.backward()
  File "/usr/local/python3/lib/python3.6/site-packages/torch/tensor.py", line 107, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph)
  File "/usr/local/python3/lib/python3.6/site-packages/torch/autograd/__init__.py", line 93, in backward
    allow_unreachable=True)  # allow_unreachable flag
RuntimeError: cuda runtime error (59) : device-side assert triggered at /pytorch/aten/src/THC/generic/THCTensorMath.cu:26

解决方法：

这种情况，一般是因为训练标签的问题。