Expected object of device type cuda but got device type cpu for argument #3 'index' in call to _th_index_select

[netblind]

GPU训练的时候报错：
Expected object of device type cuda but got device type cpu for argument #3 'index' in call to _th_index_select
Traceback (most recent call last):
File "train.py", line 431, in
main()
File "train.py", line 425, in main
train(model, device, train_list, multi_gpu, args)
File "train.py", line 319, in train
raise exception
File "train.py", line 283, in train
outputs = model.forward(input_ids=input_ids)
File "D:\ProgramData\Anaconda3\envs\pytorchspace\lib\site-packages\transformers\modeling_gpt2.py", line 533, in forward
head_mask=head_mask)
File "D:\ProgramData\Anaconda3\envs\pytorchspace\lib\site-packages\torch\nn\modules\module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "D:\ProgramData\Anaconda3\envs\pytorchspace\lib\site-packages\transformers\modeling_gpt2.py", line 420, in forward
inputs_embeds = self.wte(input_ids)
File "D:\ProgramData\Anaconda3\envs\pytorchspace\lib\site-packages\torch\nn\modules\module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "D:\ProgramData\Anaconda3\envs\pytorchspace\lib\site-packages\torch\nn\modules\sparse.py", line 114, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "D:\ProgramData\Anaconda3\envs\pytorchspace\lib\site-packages\torch\nn\functional.py", line 1484, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected object of device type cuda but got device type cpu for argument #3 'index' in call to _th_index_select

解决方案：
train.py第280行：input_ids.to(device) 修改为：input_ids = input_ids.to(device) 即可正常运行

[yangjianxin1]

我在训练时这个报错倒是还没有遇到过，谢谢

[pergrand]

请问这个问题解决了吗

[netblind]

上面有解决方案
解决方案：
train.py第280行：input_ids.to(device) 修改为：input_ids = input_ids.to(device) 即可正常运行