kenshohara / 3D-ResNets-PyTorch

3D ResNets for Action Recognition (CVPR 2018)
MIT License
3.9k stars 932 forks source link

How to execute without GPU #225

Open kpis-msa opened 4 years ago

kpis-msa commented 4 years ago

My machine has no GPU device. Then, I have the following message from this engine.

Traceback (most recent call last): File "main.py", line 428, in <module> main_worker(-1, opt) File "main.py", line 346, in main_worker model = make_data_parallel(model, opt.distributed, opt.device) File "/home/********/3D-ResNets-PyTorch/model.py", line 126, in make_data_parallel model = nn.DataParallel(model, device_ids=None).cuda() File "/home/********/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 458, in cud a return self._apply(lambda t: t.cuda(device)) File "/home/********/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 354, in _ap ply module._apply(fn) File "/home/********/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 354, in _ap ply module._apply(fn) File "/home/********/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 376, in _ap ply param_applied = fn(param) File "/home/********/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 458, in <la mbda> return self._apply(lambda t: t.cuda(device)) File "/home/********/anaconda3/lib/python3.8/site-packages/torch/cuda/__init__.py", line 186, in _lazy_i nit _check_driver() File "/home/********/anaconda3/lib/python3.8/site-packages/torch/cuda/__init__.py", line 65, in _check_d river raise AssertionError(""" AssertionError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

Please tell me how to execute this engine without GPU.

guilhermesurek commented 4 years ago

Try this flag --no_cuda.

kpis-msa commented 4 years ago

Thank you