GitLab

* Change optical flow train.py function name from validate to evaluate so it is similar to other references

* Add --device as parameter and enable to run in non distributed mode

* Format with ufmt

* Fix unneccessary param and bug

* Enable saving the optimizer and scheduler on the checkpoint

* Fix bug when evaluate before resume and save or load model without ddp

* Fix case where --train-dataset is None
Co-authored-by: Nicolas Hug <nicolashug@fb.com>

* Refactor preset transforms

* Making presets public.

* Adding prototype flag on reference scripts.

* Import prototype instead of models/transforms.

* Correcting exception type.

* fixing none referencing

Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>