Clarity On Training.

[ExponentialML]

Hello. Again, great work! I'm a little confused about the training part. You say:

To train a model run:

CUDA_VISIBLE_DEVICES=0 python run.py --config config/dataset_name.yaml --device_ids 0

Then there's this:

Then to train Animation via disentaglement (AVD) use:

CUDA_VISIBLE_DEVICES=0 python run.py --checkpoint log/{folder}/cpk.pth --config config/dataset_name.yaml --device_ids 0 --mode train_avd

Do I train the model fully (100 epoches) before moving onto the AVD training, or do I train exactly one checkpoint first, then start the AVD training? Thanks!

[AliaksandrSiarohin]

You should train until the very end.

[ExponentialML]

You should train until the very end.

Okay, thanks. Also, you might want to clarify in demo.ipynb file that you must do:

!pip install -r requirements.txt

I trained a model using the demo.ipynb as reference, and I ended up training on PyTorch 1.8.1. It led to a lot of issues after training due to the differences.