search

bm2-lab / PanPep

GNU General Public License v3.0
44 stars 9 forks source link

Torch not compiled with CUDA enabled #10

Closed haoqing12 closed 1 year ago

haoqing12 commented 1 year ago

I'm getting the following error, my server doesn't have a GPU, I've downloaded CPU-only Torch, but I still can't solve it, what should I do?

Traceback (most recent call last): File "/home/haoq/PanPep-1.0.0-beta/PanPep.py", line 164, in model = Memory_Meta(args, config).to(device) File "/home/haoq/PanPep-1.0.0-beta/Requirements/Memory_meta.py", line 213, in init self.models = torch.Tensor().cuda() File "/home/haoq/anaconda3/envs/panpep/lib/python3.9/site-packages/torch/cuda/init.py", line 210, in _lazy_init raise AssertionError("Torch not compiled with CUDA enabled") AssertionError: Torch not compiled with CUDA enabled

GaoYiChengTJ commented 1 year ago

Hi, thanks for your interest in our work. Deleting the .cuda() in line 213 may solve your problem. We are sorry for that our model can not adapt to the CPU version. We will update our model in the future.