multile gpu-error

Open vishaldhull09 opened this issue 5 years ago • 3 comments

subprocess.CalledProcessError: Command '['/home/payal/anaconda3/envs/spn/bin/python', '-u', 'tools/train.py', '--local_rank=1', './configs/sp.py', '--launcher', 'pytorch']' returned non-zero exit status 1.

Any idea how to resolve this

Oct 23 '20 08:10 vishaldhull09

@vishaldhull09 Have you tried to use single GPU training?

Oct 23 '20 12:10 yan-roo

Yes it's working fine

Oct 23 '20 12:10 vishaldhull09

https://github.com/open-mmlab/mmdetection/issues/3423 https://github.com/open-mmlab/mmdetection/issues/1293 https://github.com/open-mmlab/mmdetection/issues/878

Maybe you can check your GPU usage by nvidia-smi? Is there any process working in the same time?

Oct 23 '20 16:10 yan-roo