Batch Size advice

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.

User avatar
Posts: 42
Joined: Sat Aug 15, 2020 2:43 am
Has thanked: 4 times

Batch Size advice

Post by dheinz70 »

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.

User avatar
Posts: 1495
Joined: Fri Jul 12, 2019 12:53 am
Answers: 127
Has thanked: 51 times
Been thanked: 287 times

Re: Batch Size advice

Post by torzdf »

The general working theory is that bigger batches generalize better, smaller batches are better at catching differences between images.

My word is final