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.
dheinz70
Posts: 43 Joined: Sat Aug 15, 2020 2:43 am
Has thanked: 4 times
Post
by dheinz70 » Wed Jun 02, 2021 9:01 pm
Is there any benefit to stepping down the batch size as the model learns? My general recipe is run at max batch size for a few days, cut that batch size in 1/2 for a few more. Then remove warping and cut that batch size in 1/2 again and run for a day.
What do you find works best? Thanks in advance.
torzdf
Posts: 2682 Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 133 times
Been thanked: 626 times
Post
by torzdf » Thu Jun 03, 2021 9:56 am
The general working theory is that bigger batches generalize better, smaller batches are better at catching differences between images.