AssertionError: Torch not compiled with CUDA enabled

carpedm20 / ENAS-pytorch

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

Apache License 2.0

2.69k stars 492 forks source link

AssertionError: Torch not compiled with CUDA enabled #38

Open zhjmcjk opened 5 years ago

zhjmcjk commented 5 years ago

I try to run the ptb example using the command: (No GPU on my laptop) python main.py --network_type rnn --dataset ptb --num_gpu 0

The program ran for a while, and an error occurred. Can anyone give me some advice? Thanks!

CesurMurka commented 5 years ago

have you resolved this? I have the same issue

NdaAzr commented 5 years ago

@CesurMurka and @zhjmcjk I didn't reach this stage, and I got this error. How did you resolve this? If you didn't get an error could you please mention your Pytorch version?

File "main.py", line 30, in main trnr = trainer.Trainer(args, dataset) File "D:\Neda\Pytorch\NAS\trainer.py", line 160, in __init__ self.build_model() File "D:\Neda\Pytorch\NAS\trainer.py", line 182, in build_model self.shared = models.RNN(self.args, self.dataset) AttributeError: module 'models' has no attribute 'RNN'

martsalz commented 5 years ago

I have the same issue