eda6433936
refactoring
2020-03-08 23:19:04 +04:00
121c0cfc0f
FANSeg : reverting to use it the same as in DFL 1.0
2020-03-08 22:25:11 +04:00
c371818eef
upd README.md
2020-03-08 15:18:39 +04:00
32f66ebc65
upd README.md
2020-03-08 15:17:32 +04:00
cc87c3ce1d
upd README.md
2020-03-08 15:12:29 +04:00
cfea601877
upd README.md
2020-03-08 15:05:28 +04:00
d5c29b55e3
upd README.md
2020-03-08 14:48:19 +04:00
22b0865455
upd FANSeg
2020-03-08 10:47:04 +04:00
18d93376fc
update FANSeg
2020-03-08 10:34:48 +04:00
6f4ea69d4d
added dev_segmented_extract,
...
extracts marked images in 'labelme' tool, that can be used in FANseg training
2020-03-08 10:13:15 +04:00
143792fd31
added fanseg for future WF segmentation model
2020-03-08 00:49:12 +04:00
3b6ad4abf9
refactoring
2020-03-07 20:51:54 +04:00
d6a685887f
fix nick
2020-03-07 19:20:07 +04:00
d0c280a902
fix
2020-03-07 16:33:50 +04:00
45270f3fb5
SAEHD:
...
added new experimental arhi
'liaech' - made by @chervoniy. Based on liae, but produces more src-like face.
2020-03-07 16:06:10 +04:00
0bac399841
update leras
2020-03-07 16:05:53 +04:00
123bccf01a
returned back
...
3.optional) denoise data_dst images.bat
Apply it if dst video is very sharp.
Denoise dst images before face extraction.
This technique helps neural network not to learn the noise.
The result is less pixel shake of the predicted face.
2020-03-07 15:51:30 +04:00
ada60ccefe
code refactoring,
...
lr_dropout is now disabled in pretraining mode
changed help message for lr_dropout and random_warp
2020-03-07 13:59:47 +04:00
9ccdd271a4
added sort by "best faces faster"
...
same as sort by "best faces"
but faces will be sorted by source-rect-area instead of blur, x40 times faster.
2020-03-06 21:38:41 +04:00
54548afe1a
refactoring
2020-03-06 01:21:38 +04:00
9365e42f25
trainer now creates directories instead of throwing error when they do not exist
2020-03-04 17:54:52 +04:00
cd76425db3
update leras
2020-03-04 15:08:10 +04:00
302d23a612
refactoring
2020-03-03 22:20:15 +04:00
f56d583cb5
added sort by "face rect size in source image"
...
small faces from source image will be placed at the end
2020-03-03 21:47:49 +04:00
780ad5679f
fix --force-gpu-idxs commandline param for trainer
2020-03-03 21:25:24 +04:00
82bc724077
upd README.md
2020-03-03 17:17:08 +04:00
8a3e1c2e29
upd README.md
2020-03-03 17:16:00 +04:00
e1e9beb722
Merge branch 'master' of https://github.com/iperov/DeepFaceLab
2020-03-03 17:11:17 +04:00
d1f942d6dd
upd README.md
2020-03-03 17:10:25 +04:00
8b5718c481
Set theme jekyll-theme-cayman
2020-03-02 17:53:15 +04:00
036f6cdeb4
upd README.md
2020-03-02 17:48:13 +04:00
130c33d965
upd README.md
2020-03-02 17:06:06 +04:00
884913e35d
upd leras
2020-03-02 07:09:39 +04:00
757ec77e44
refactoring
2020-03-01 19:09:50 +04:00
cbff72f597
_
2020-02-29 15:53:48 +04:00
6d122fd742
_
2020-02-29 15:50:17 +04:00
516e23584e
_
2020-02-29 15:48:31 +04:00
803f7f9717
_
2020-02-29 15:40:11 +04:00
b093112f2f
_
2020-02-29 15:39:43 +04:00
a21c55cf25
_
2020-02-29 15:36:37 +04:00
f55a65c304
_
2020-02-29 15:34:27 +04:00
55162d6e6c
_
2020-02-29 15:32:36 +04:00
2af067b18d
_
2020-02-29 15:25:49 +04:00
27e24d5d28
_
2020-02-29 15:24:14 +04:00
c900c65c31
_
2020-02-29 15:20:17 +04:00
63c0bdbf16
)_
2020-02-29 15:10:59 +04:00
98d3657cbc
_
2020-02-29 15:00:46 +04:00
7f609d0f0a
fix for linux
2020-02-29 14:49:46 +04:00
dbf28eeebf
fix for linux
2020-02-29 14:36:10 +04:00
5eca4958b7
fix for linux
2020-02-29 14:34:08 +04:00
Colombo