Traceback (most recent call last):
File "E:/relate_code/Gaitpart-master/main.py", line 149, in <module>
train_model()
File "E:/relate_code/Gaitpart-master/main.py", line 98, in train_model
loss = criterion(outputs, labels)
File "C:\Anaconda3\envs\gaitpart\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Anaconda3\envs\gaitpart\lib\site-packages\torch\nn\modules\loss.py", line 1163, in forward
return F.cross_entropy(input, target, weight=self.weight,
File "C:\Anaconda3\envs\gaitpart\lib\site-packages\torch\nn\functional.py", line 2996, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'
loss计算时,数据类型出错,将:
loss = criterion(outputs, labels)
修改为:
loss = criterion(outputs, labels.long())
即可解决!
日常学习记录,一起交流讨论吧!侵权联系~