Open francescosarno opened 1 year ago
Did you work in the provided docker environment? You can bypass the torch.multiprocessing by modifying our training code. Or just directly cal the function eval() could also works. https://github.com/DecaYale/RNNPose/blob/main/tools/eval.py#:~:text=def%20eval-,(,-config_path%2C I hope this could be helpful for debugging. Thanks.
I have a problem running
bash scripts/eval.sh
:The terminal is frozen and I cannot see what is going on. I tried using
pdb
in order to put breakpoints, but this rises errors withtorch.multiprocessing
. Did anyone have the same problem?