46ff33bf89
SAE: dssim kernel size now depends on resolution
2019-03-12 09:49:40 +04:00
fd3b9add2f
SAE: added option "simple optimizer" allows to train bigger networks on same VRAM
...
nnlib: added DFLOptimizer is my own optimizer
2019-03-12 09:32:35 +04:00
3bad8dd8ec
fix
2019-03-11 21:53:28 +04:00
ee8dbcbc35
revert back Adam
2019-03-11 21:52:36 +04:00
e4637336ef
added ability to save optimizers states which work with K.function,
...
added custom Adam that can save 'iterations' param
2019-03-11 18:23:01 +04:00
714d4f0fca
small fix
2019-03-03 16:42:13 +04:00
31c2298b5f
Converter: added option for seamless to supress jittering,
...
Lenx,leny region now averaged by grayscale gradients,
now uses all CPU.
SAE: multiscale_decoder option default = False
update readme and manual_ru.pdf
2019-03-03 15:33:52 +04:00
438213e97c
manual extractor: increased FPS,
...
sort by final : now you can specify target number of images,
converter: fix seamless mask and exception,
huge refactoring
2019-02-28 11:56:31 +04:00
65752e044b
SAE: added support 64-256 resolution multiple of 16
2019-02-21 20:44:55 +04:00
a858732b1d
refactoring
2019-02-21 20:06:04 +04:00
97685ce0ae
added saving model_summary.txt
2019-02-21 19:55:44 +04:00
f0a20b46d3
SAE: added new archi 'vg'
2019-02-21 17:53:59 +04:00
72ba6b103c
added support of AMD videocards
...
added Intel's plaidML backend to use OpenCL engine. Check new requirements.
smart choosing of backend in device.py
env var 'force_plaidML' can be choosed to forced using plaidML
all tf functions transferred to pure keras
MTCNN transferred to pure keras, but it works slow on plaidML (forced to CPU in this case)
default batch size for all models and VRAMs now 4, feel free to adjust it on your own
SAE: default style options now ZERO, because there are no best values for all scenes, set them on your own.
SAE: return back option pixel_loss, feel free to enable it on your own.
SAE: added option multiscale_decoder default is true, but you can disable it to get 100% same as H,DF,LIAEF model behaviour.
fix converter output to .png
added linux fork reference to doc/doc_build_and_repository_info.md
2019-02-19 17:33:12 +04:00
535041f7bb
upd
2019-02-12 10:55:41 +04:00
429e7e6aee
upd nnlib.py
2019-02-12 09:30:38 +04:00
6c944d8989
upd readme
2019-02-11 21:26:51 +04:00
470fb9287a
SAE: remove rare sample booster. DSSIM->MSE transition now between 5-20k epochs.
2019-02-11 17:18:01 +04:00
af3dd59f67
SAE: remove multiscale decoder option, default - true
2019-02-11 10:36:02 +04:00
854ab11de3
fix bug with samples that were not clipped after tanh-untanh transformations, upd README.md
2019-02-10 10:45:51 +04:00
51a13c90d1
SAE: you have to restart training,
...
added multiscale decoder as option.
mask now training as not multiscaled
2019-02-09 20:33:26 +04:00
4d37fd62cd
fix DFLJPG,
...
SAE: added "rare sample booster"
SAE: pixel loss replaced to smooth transition from DSSIM to PixelLoss in 15k epochs by default
2019-02-09 18:53:37 +04:00
c3b6330284
SAE: now asking face_type after resolution
2019-02-05 15:00:27 +04:00
883da4b9ed
fix Util.py, SAE: lowest ae dims now can be 32 (for testing)
2019-02-05 14:43:54 +04:00
241ae83e0b
upd readme
2019-02-05 13:27:18 +04:00
707313eb47
SAE+ConverterMasked now offer default values such as mode, erode, blur, values based on model settings.
2019-02-03 21:44:30 +04:00
e226ab5385
SAE: increased speed of training by 10-18%,
...
increased clipping border mask in full face mode results better transition of cheeks,
default archi now 'df'
2019-02-03 20:32:46 +04:00
541d6e1cc9
nothing interesting
2019-01-26 06:50:52 +04:00
e5b14672ee
SAE: upd help for new 'pixel loss' option
2019-01-25 10:02:30 +04:00
ef3cf392c5
SAE: added pixel loss option.
2019-01-25 09:56:40 +04:00
7f4d261a99
change SAE help message
2019-01-22 18:31:00 +04:00
6d7c56309d
SAE: removed adaptive kernel size. No backward compatibility.
2019-01-22 13:30:38 +04:00
fe66b6b2a1
SAE: added 'learn mask' option, default:Y,
...
SAE: added clipping mask at borders to remove artifact lines.
2019-01-19 16:15:49 +04:00
dd10d963d1
SAE: upd default params, upd readme
2019-01-19 08:58:25 +04:00
946688567d
enhanced SAE model. You should to restart training.
...
new default style power = 2.0
fix DF default batch sizes.
upd readme
2019-01-17 21:41:40 +04:00
ba06a71fff
SAE: changed default style power to 10.0 . Now style power is floating number in valid range 0.0 to 100.0
2019-01-14 21:24:33 +04:00
b68612e6cd
SAE: 'adaptive kernel size' now as an option
2019-01-13 10:03:01 +04:00
46aa61050a
improvement SAE model. New option added. You should to restart training.
2019-01-12 10:10:50 +04:00
32f0db3dea
fix and upd readme
2019-01-11 06:19:15 +04:00
e39d1a2619
fixes
2019-01-10 23:01:33 +04:00
f82bc7031e
fix SAE
2019-01-10 19:29:17 +04:00
bf5282f7ec
if you have multi GPU in a system, you can choose what GPU to use on model start
2019-01-10 19:22:54 +04:00
48d0123f0b
SAE: new options face_style_power, bg_style_power instead of style_power. Zero - means dont use style.
...
SAE: new option 'lighter_encoder'.
Now model settings can be overrided by pressing enter in 2 seconds while model loading (works on Windows).
Removed all MultiGPU models, because keras multi_gpu in fact doesn't work.
2019-01-10 18:28:12 +04:00
00d7a3ab4d
sae: removing mask in preview window
2019-01-09 11:24:58 +04:00
e300662f89
SAE: added options archi, learn_face_style , learn_bg_style, style_power
2019-01-09 10:51:31 +04:00
0c3559d2dd
fix sae
2019-01-09 10:46:12 +04:00
1a2555e160
added '?' help for model options. Added 'Src face scale modifier' to model options.
2019-01-09 09:22:22 +04:00
75f7a9575a
SAE: changed base erode/blur mask size for converter
2019-01-07 17:46:50 +04:00
3b0b1a7dec
removed UFM model,
...
added 'random_flip' option to all models, by default - true
2019-01-06 19:59:53 +04:00
8e1d337e00
added new SAE model - Styled AutoEncoder
2019-01-05 09:57:49 +04:00
iperov