Hi.
I am training a model with has gone through 400k iterations. The output is also decent. But I have better videos of face A and face B , how can I add these new data and continue from 400k iterations. Should I make a new video combining old data + new data and then extract it so that alignments of overall data be created ? Or is there a better way?
How to add more data to face A and face B while training has started?
Forum rules
Read the FAQs and search the forum before posting a new topic.
This forum is for discussing tips and understanding the process involved with Training a Faceswap model.
If you have found a bug are having issues with the Training process not working, then you should post in the Training Support forum.
Please mark any answers that fixed your problems so others can find the solutions.
-
darecracker
- Posts: 1
- Joined: Mon Jun 19, 2023 8:46 pm
How to add more data to face A and face B while training has started?
Re: How to add more data to face A and face B while training has started?
Just:
- Stop the model training.
- Extract your new faces.
- Add the new faces to your training folder.
- Resume training
That's it.
My word is final