Improving quality of sources as training progresses

Want to understand the training process better? Got tips for which model to use and when? This is the place for you


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.

Locked
User avatar
aolvera27
Posts: 27
Joined: Thu May 27, 2021 3:53 am
Answers: 1
Has thanked: 5 times
Been thanked: 6 times

Improving quality of sources as training progresses

Post by aolvera27 »

I wasn't sure how to phrase this in the title, but I'm wondering how good of a strategy would be to start training with no so good sources the first 20k iterations, and stick to the best ones for the remainder of the process.

Right now I have 1400 very good faces of B, with a wide variety of lightning conditions, but they're lacking some angles. I'm thinking of adding some 600 not so great faces with those missing angles, and drop them as I hit the 20k iterations. My intention is to provide the main forms of the face at those angles, but I don't know how much it would hurt the model.

What do you think? I want to try it out unless you tell me it's decisively a bad idea with a certainty of failure.

User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Improving quality of sources as training progresses

Post by bryanlyon »

This is an aspect of what I call "fit training". See the guide viewtopic.php?f=27&t=74 for some more explanation of the process. Basically once fully trained, you train on just the swap video (and in your case, your best data for B) and let it try to master the detail.

User avatar
aolvera27
Posts: 27
Joined: Thu May 27, 2021 3:53 am
Answers: 1
Has thanked: 5 times
Been thanked: 6 times

Re: Improving quality of sources as training progresses

Post by aolvera27 »

Great, thanks!

I actually read that guide (I've been trying to read everything on the forums, even the technical stuff I don't get), but I didn't realize this approach could be considered a particular case of fit training.

Locked