I have the problem:
Traceback (most recent call last):
File “train_2.py”, line 44, in
trainer.run()
File “train_2.py”, line 27, in run
outputs = self.model(inputs)
File “C:\Users\lili\Anaconda3\envs\python3-torch\lib\site-packages\torch\nn\modules\module.py”, line 489, in call
result = self.forward(*input, **kwargs)
File “C:\Users\lili\workspace\用tensorflow进行中文自然语言处理的情感分析\chinese_sentiment-master\qa_code\qafa.py”, line 20, in forward
question = self.dense1(question)
File “C:\Users\lili\Anaconda3\envs\python3-torch\lib\site-packages\torch\nn\modules\module.py”, line 489, in call
result = self.forward(*input, **kwargs)
File “C:\Users\lili\Anaconda3\envs\python3-torch\lib\site-packages\torch\nn\modules\linear.py”, line 67, in forward
return F.linear(input, self.weight, self.bias)
File “C:\Users\lili\Anaconda3\envs\python3-torch\lib\site-packages\torch\nn\functional.py”, line 1352, in linear
ret = torch.addmm(torch.jit._unwrap_optional(bias), input, weight.t())
RuntimeError: cublas runtime error : library not initialized at …\aten\src\THC\THCGeneral.cpp:250
I am using single GPU.I have tried “sudo rm -rf ~/.nv” and it didn’t work. I am confused. Hop