Open jhj0517 opened 5 months ago
Changed:
mmcv
torch
decord
xformers
Tested with
python pose_align.py --imgfn_refer ./assets/images/ref.png --vidfn ./assets/videos/dance.mp4 python test_stage_2.py --config ./configs/test_stage_2.yaml -W 512 -H 512
in venv and confirmed that it works fine.
Changed:
mmcv
s in requirementstorch
versions with CUDA 12.1decord
on MacOS.xformers
to latest compatible versionTested with
in venv and confirmed that it works fine.