Colombo
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
Colombo
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
Colombo
54548afe1a
refactoring
2020-03-06 01:21:38 +04:00
Colombo
9365e42f25
trainer now creates directories instead of throwing error when they do not exist
2020-03-04 17:54:52 +04:00
Colombo
cd76425db3
update leras
2020-03-04 15:08:10 +04:00
Colombo
302d23a612
refactoring
2020-03-03 22:20:15 +04:00
Colombo
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
Colombo
780ad5679f
fix --force-gpu-idxs commandline param for trainer
2020-03-03 21:25:24 +04:00
Colombo
82bc724077
upd README.md
2020-03-03 17:17:08 +04:00
Colombo
8a3e1c2e29
upd README.md
2020-03-03 17:16:00 +04:00
Colombo
e1e9beb722
Merge branch 'master' of https://github.com/iperov/DeepFaceLab
2020-03-03 17:11:17 +04:00
Colombo
d1f942d6dd
upd README.md
2020-03-03 17:10:25 +04:00
iperov
8b5718c481
Set theme jekyll-theme-cayman
2020-03-02 17:53:15 +04:00
Colombo
036f6cdeb4
upd README.md
2020-03-02 17:48:13 +04:00
Colombo
130c33d965
upd README.md
2020-03-02 17:06:06 +04:00
Colombo
884913e35d
upd leras
2020-03-02 07:09:39 +04:00
Colombo
757ec77e44
refactoring
2020-03-01 19:09:50 +04:00
Colombo
cbff72f597
_
2020-02-29 15:53:48 +04:00
Colombo
6d122fd742
_
2020-02-29 15:50:17 +04:00
Colombo
516e23584e
_
2020-02-29 15:48:31 +04:00
Colombo
803f7f9717
_
2020-02-29 15:40:11 +04:00
Colombo
b093112f2f
_
2020-02-29 15:39:43 +04:00
Colombo
a21c55cf25
_
2020-02-29 15:36:37 +04:00
Colombo
f55a65c304
_
2020-02-29 15:34:27 +04:00
Colombo
55162d6e6c
_
2020-02-29 15:32:36 +04:00
Colombo
2af067b18d
_
2020-02-29 15:25:49 +04:00
Colombo
27e24d5d28
_
2020-02-29 15:24:14 +04:00
Colombo
c900c65c31
_
2020-02-29 15:20:17 +04:00
Colombo
63c0bdbf16
)_
2020-02-29 15:10:59 +04:00
Colombo
98d3657cbc
_
2020-02-29 15:00:46 +04:00
Colombo
7f609d0f0a
fix for linux
2020-02-29 14:49:46 +04:00
Colombo
dbf28eeebf
fix for linux
2020-02-29 14:36:10 +04:00
Colombo
5eca4958b7
fix for linux
2020-02-29 14:34:08 +04:00
Colombo
fcbfbdd560
_
2020-02-29 14:31:21 +04:00
Colombo
10ffca37c0
_
2020-02-29 14:27:02 +04:00
Colombo
6b6aaba4db
ignore UserWarning for platforms != win32
2020-02-29 14:24:25 +04:00
Colombo
7e276a4ec7
_
2020-02-29 14:12:53 +04:00
Colombo
7180076ecf
fix
2020-02-29 13:31:36 +04:00
Colombo
e9c0f5fb9f
upd README.md
2020-02-29 12:59:24 +04:00
Colombo
90ae68ae61
fix input_in_time for linux
2020-02-29 11:05:04 +04:00
Colombo
72797ce406
linux support ffmpeg aac "strict": "experimental"
2020-02-29 08:55:17 +04:00
Colombo
c1bf3f53ba
add comment
2020-02-28 19:31:33 +04:00
Colombo
f88c45d338
fix saehd for multi gpu
2020-02-27 23:06:06 +04:00
Colombo
74999ce7ee
SAEHD:
...
'models_opt_on_gpu' option is now available for multigpus (before only for 1 gpu)
max resolution is now 512
2020-02-27 16:21:32 +04:00
Colombo
810dc5ada5
Extractor: image size for all faces now 512
2020-02-27 16:20:37 +04:00
Colombo
59be114485
upd leras
2020-02-27 16:20:14 +04:00
Colombo
acb0b34811
revert
2020-02-27 12:03:01 +04:00
Colombo
30c93a9bdb
fix
2020-02-27 11:41:06 +04:00
Colombo
8ad1481209
_
2020-02-27 11:39:29 +04:00
Colombo
c7ab9653c5
new optimized training:
...
for every batch_size*16 samples,
model collects the samples with the highest error and learns them again
therefore hard samples will be trained more often
2020-02-27 11:19:53 +04:00