wei-tim / YOWO

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
Other
846 stars 158 forks source link

About the envs setup #81

Open yangsuhui opened 3 years ago

yangsuhui commented 3 years ago

good job! But what environments should I setup to run this code? such as the versions of pytorch? Thanks

aikuniverse commented 3 years ago

I have the same problem

eneserdo commented 2 years ago

I only installed these and it works

pip install fvcore
conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch # Currently it is pytorch 1.12
pip install opencv-python==4.6.0.66