github/DeepFaceLive
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLive synced 2025-08-14 10:47:00 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

upd

Browse source
This commit is contained in:
iperov 2021-09-19 12:38:37 +04:00
commit 84f3407198
1 changed files with 1 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

13
doc/user_faq/user_faq.md
View file

@ -71,18 +71,7 @@ Make a backup before every stage !
> Using SAEHD model.
res:224, WF, ae_dims:256, e_dims:64, d_dims:64, d_mask_dims 22, eyes_mouth_prio:Y, batch more is better. Others are default.
Assuming 1kk iters with batch 8. If the batch is higher, iters is possible less.
1) enable pretrain mode. Train to 1kk
2) disable pretrain mode. Train to 1kk
3) lrd:N uniform_yaw:True, color_transfer:lct, train +500..800k
4) lrd:Y train +500..800k iters
5) disable random warp +500..800k iters
6) enable gan 0.1 gan_dims:32, train +100..300k iters
You can reuse this model to train new src faceset. In this case you must delete the file inter_AB.npy from the model folder, and train from stage 3.
-- coming soon --
> Using AMP model.