I encountered this problem when I try to train on a single Gpu, please help me,Thank you :
python main_persformer.py --mod=kkk --batch_size=8 --nepochs=200
proc_id: None
world size: 1
local_rank: None
None
Traceback (most recent call last):
File "main_persformer.py", line 40, in
main()
File "main_persformer.py", line 30, in main
ddp_init(args)
File "/media/lee/PersFormer_3DLane-main/experiments/ddp.py", line 80, in ddp_init
setup_distributed(args)
File "/media/lee/PersFormer_3DLane-main/experiments/ddp.py", line 63, in setup_distributed
torch.cuda.set_device(args.gpu)
File "/media/lee/miniconda3/envs/cc/lib/python3.7/site-packages/torch/cuda/init.py", line 309, in set_device
device = _get_device_index(device)
File "/media/lee/miniconda3/envs/cc/lib/python3.7/site-packages/torch/cuda/_utils.py", line 34, in _get_device_index
return _torch_get_device_index(device, optional, allow_cpu)
File "/media/lee/miniconda3/envs/cc/lib/python3.7/site-packages/torch/_utils.py", line 514, in _get_device_index
'or an integer, but got:{}'.format(device))
ValueError: Expected a torch.device with a specified index or an integer, but got:None
OpenDriveLab
