github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-07-07 13:32:09 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

upd readme

Browse source
This commit is contained in:
iperov 2018-12-18 23:22:00 +04:00
parent 26571eff6a
commit f32a44a778
1 changed files with 7 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

12
README.md
View file

@ -114,6 +114,8 @@ Conclusion: **better not to mix and use only same shape faces with same light**
### **Sort tool**: ### **Sort tool**:
`blur` places most blurred faces at end of folder
`hist` groups images by similar content `hist` groups images by similar content
`hist-dissim` places most similar to each other images to end. `hist-dissim` places most similar to each other images to end.
@ -124,15 +126,15 @@ Conclusion: **better not to mix and use only same shape faces with same light**
`hue` `hue`
`face` and `face-dissim` currently useless `black` Places images which contains black area at end of folder. Useful to get rid of src faces which cutted by screen.
Best practice for gather src faceset: Best practice for gather src faceset:
1) delete first unsorted aligned groups of images what you can to delete. Dont touch target face mixed with others. 1) delete first unsorted aligned groups of images what you can to delete. Dont touch target face mixed with others.
2) `blur` -> delete ~half of them 2) `black` -> delete faces cutted by black area at end of folder
3) `hist` -> delete groups of similar and leave only target face 3) `blur` -> delete 30-50% at end of folder
4) `hist-blur` -> delete blurred at end of groups of similar 4) `hist` -> delete groups of similar and leave only target face
5) `hist-dissim` -> leave only first **1000-1500 faces**, because number of src faces can affect result. For YAW feeder model skip this step. 5) `hist-dissim` -> leave only first **1500 faces**
6) `face-yaw` -> just for finalize faceset 6) `face-yaw` -> just for finalize faceset
Best practice for dst faces: Best practice for dst faces: