facebookresearch / TimeSformer

The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
Other
1.57k stars 213 forks source link

Finetuning code can be improved #133

Closed feemthan closed 7 months ago

feemthan commented 7 months ago

in line 418, if not cfg.TRAIN.FINETUNE: should be if cfg.TRAIN.FINETUNE:

feemthan commented 7 months ago

https://github.com/facebookresearch/TimeSformer/pull/134

PBhat07 commented 7 months ago

Thank you so much ! I was facing issue with resuming my training. This correction solved it.