david/DeepFaceLab_Linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
202 Commits 1 Branch 0 Tags
707313eb476bedc4dd90902a342fe19c595fd733
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
iperov 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
iperov 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
iperov 41abda42d2 SampleProcessor now uses CUBIC interpolation (was LANCSOZ4) in order to reduce CPU usage 2019-02-03 19:19:42 +04:00
iperov 541d6e1cc9 nothing interesting 2019-01-26 06:50:52 +04:00
iperov 7ed7f2bab9 fixed bug in manual extractor on windows 10 2019-01-26 06:20:47 +04:00
iperov 5ed1637acb upd readme 2019-01-25 20:21:38 +04:00
iperov e5b14672ee SAE: upd help for new 'pixel loss' option 2019-01-25 10:02:30 +04:00
iperov ef3cf392c5 SAE: added pixel loss option. 2019-01-25 09:56:40 +04:00
iperov 72646becd1 forcing all tqdm's to ascii in order to work properly on Chinese windows 2019-01-24 21:32:07 +04:00
iperov 1e7a0836f7 nothing interesting 2019-01-24 21:28:54 +04:00
iperov 403343e465 upd ISSUE_TEMPLATE.md 2019-01-24 15:15:56 +04:00
iperov 1a01b7d401 upd readme 2019-01-23 20:40:16 +04:00
iperov 318e6608f7 Extractor: increased speed of deleted debug files searcher 2019-01-23 09:48:45 +04:00
iperov 6c06e60de4 upd readme: added advanced tips by @GAN-er 2019-01-22 22:13:06 +04:00
iperov 2029171342 upd readme 2019-01-22 18:41:02 +04:00
iperov 7f4d261a99 change SAE help message 2019-01-22 18:31:00 +04:00
iperov 21460c2e13 upd manual extractor help message 2019-01-22 18:15:55 +04:00
iperov 6d7c56309d SAE: removed adaptive kernel size. No backward compatibility. 2019-01-22 13:30:38 +04:00
iperov 66390335d6 upd readme: added SAE asian face preview 2019-01-22 13:15:25 +04:00
iperov 2571f23bc4 Extractor added new feature --manual-output-debug-fix, 
Performs manual reextract input-dir frames which were deleted from [output_dir]_debug\ dir.
 2019-01-22 12:46:54 +04:00
iperov b6c4171ea1 optimizations of nnlib and SampleGeneratorFace, 
refactorings
 2019-01-22 11:52:04 +04:00
iperov 2de45083a4 temporally forcing requirement of numpy version to 1.15.4 2019-01-22 11:16:55 +04:00
iperov 3bbc008207 change jpeg quality to 50% 2019-01-22 10:05:20 +04:00
iperov 8016ee32cc change aligned_debug files from png to jpg 2019-01-22 09:55:41 +04:00
iperov 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
iperov dd10d963d1 SAE: upd default params, upd readme 2019-01-19 08:58:25 +04:00
iperov 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
iperov 22401cecfc fix H128 2019-01-15 17:52:54 +04:00
iperov 123b3d3d23 upd comm group 2019-01-15 13:49:50 +04:00
iperov 7545a615cc added chinese comm group 2019-01-15 13:36:58 +04:00
iperov 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
iperov 7233b24d2c upd readme 2019-01-14 19:53:27 +04:00
iperov c3e35d4259 upd readme 2019-01-14 13:16:55 +04:00
iperov 1f2b1481ef now you can train models on multiple GPU's on same workspace without cloning any folders. 
Model files names will be prefixed with GPU index if GPU choosed explicitly on train/convert start.
if you leave GPU idx choice default, then best GPU idx will be choosed and model file names will not contain index prefix.
It gives you possibility to train same fake with various models or options on multiple GPUs.

H64 and H128: now you can choose 'Lighter autoencoder'. It is same as vram gb <= 4 before this update.

added archived_models.zip contains old experiments

RecycleGAN: archived

devicelib: if your system has no NVML installed (some old cards), then it will work with gpu_idx=0 as 'Generic GeForce GPU' with 2GB vram.

refactorings
 2019-01-14 10:48:23 +04:00
iperov e2f4677987 upd readme 2019-01-13 22:04:05 +04:00
iperov d2d068c168 upd readme 2019-01-13 17:47:48 +04:00
iperov e0605df175 upd readme 2019-01-13 17:47:05 +04:00
iperov 12383570e8 Fix for systems without NVSMI 2019-01-13 16:38:17 +04:00
iperov 4625bcec1c fix multigpu extractor 2019-01-13 13:59:22 +04:00
iperov 91bb5221d4 upd donate 2019-01-13 11:07:38 +04:00
iperov 36d6935fc6 upd donate 2019-01-13 11:03:02 +04:00
iperov b68612e6cd SAE: 'adaptive kernel size' now as an option 2019-01-13 10:03:01 +04:00
iperov ae9fe12c59 added bitcoin donate address 2019-01-12 19:46:11 +04:00
iperov 81e837d920 upd readme 2019-01-12 15:29:34 +04:00
iperov da0af0f35e added donate button. Goal: buy RTX 2080 TI 2019-01-12 14:32:05 +04:00
iperov 46aa61050a improvement SAE model. New option added. You should to restart training. 2019-01-12 10:10:50 +04:00
iperov 2473dabf37 fix loss history 2019-01-11 19:19:29 +04:00
iperov e6fa021c3d fix prompt override model settings in convert mode 2019-01-11 11:29:18 +04:00
iperov 32f0db3dea fix and upd readme 2019-01-11 06:19:15 +04:00
iperov e39d1a2619 fixes 2019-01-10 23:01:33 +04:00
iperov 127cc3303a upd README.md 2019-01-10 20:28:14 +04:00
iperov bd2b575718 fix ModelBase.py 2019-01-10 19:38:31 +04:00
iperov f82bc7031e fix SAE 2019-01-10 19:29:17 +04:00
iperov 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
iperov 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
iperov c3f175862a fix manual extractor bug 2019-01-10 05:12:02 +04:00
iperov 390fa12d6f update readme for raw mode of converter 2019-01-09 14:26:04 +04:00
iperov 1e28ae24b1 Fix bug in ConverterMasked when overexposed pixels appear sometimes 2019-01-09 13:57:26 +04:00
iperov faa8cebc98 fix 'raw' mode in ConverterMasked 2019-01-09 13:40:33 +04:00
iperov 42f0e438f3 added 'raw' mode to convertermasked 2019-01-09 13:35:10 +04:00
iperov 1c601dce4a fix converter bug when blur size == 0 2019-01-09 12:10:29 +04:00
iperov 00d7a3ab4d sae: removing mask in preview window 2019-01-09 11:24:58 +04:00
iperov e300662f89 SAE: added options archi, learn_face_style , learn_bg_style, style_power 2019-01-09 10:51:31 +04:00
iperov 0c3559d2dd fix sae 2019-01-09 10:46:12 +04:00
iperov 1a2555e160 added '?' help for model options. Added 'Src face scale modifier' to model options. 2019-01-09 09:22:22 +04:00
iperov e8620919a7 update devicelib/nnlib to detect compute capability 2019-01-08 10:48:06 +04:00
iperov 29c2375f5a upd readme 2019-01-08 10:00:31 +04:00
iperov 75f7a9575a SAE: changed base erode/blur mask size for converter 2019-01-07 17:46:50 +04:00
iperov 104651b292 upd readme 2019-01-07 17:28:58 +04:00
iperov cf41e1b962 fix sort by final 2019-01-07 17:27:10 +04:00
iperov ff3a208e80 fix sort by final 2019-01-07 14:57:46 +04:00
iperov cce2e8a0ba upd readme 2019-01-07 14:35:52 +04:00
iperov abdbe7fd8d added sort by 'final' 2019-01-07 14:20:44 +04:00
iperov 6faabcb94e DF: fix default mask 2019-01-07 10:13:50 +04:00
iperov 12dd7fcae5 fixed sort by yaw feeder 2019-01-07 09:40:00 +04:00
iperov 3b0b1a7dec removed UFM model, 
added 'random_flip' option to all models, by default - true
 2019-01-06 19:59:53 +04:00
iperov 1a13c5eaa9 upd readme 2019-01-05 19:40:48 +04:00
iperov 7555d78ae1 upd readme 2019-01-05 10:07:52 +04:00
iperov 8e1d337e00 added new SAE model - Styled AutoEncoder 2019-01-05 09:57:49 +04:00
iperov b5ba7d52cb increased speed of sort by hist sim for ten thousands of faces 2019-01-04 22:54:09 +04:00
iperov 08550ac856 fix H128 after refactoring 2019-01-04 18:28:07 +04:00
iperov 1398072427 upd readme 2019-01-04 00:09:39 +04:00
iperov 69d5b1e662 fix UFM 2019-01-03 23:02:38 +04:00
iperov 8456122cb2 upd 2019-01-03 22:15:10 +04:00
iperov 8a0e47bd6e upd readme 2019-01-03 09:45:01 +04:00
iperov 57e1e59c03 revert sort_by_hist 2019-01-02 23:53:27 +04:00
iperov 5f80ea0513 added missing file 2019-01-02 18:38:11 +04:00
iperov 7b70e7eec1 added new model U-net Face Morpher. 
removed AVATAR - useless model was just for demo
removed MIAEF128 - use UFM insted
removed LIAEF128YAW - use model option sort by yaw on start for any model
All models now ask some options on start.
Session options (such as target epoch, batch_size, write_preview_history etc) can be overrided by special command arg.
Converter now always ask options and no more support to define options via command line.
fix bug when ConverterMasked always used not predicted mask.
SampleGenerator now always generate samples with replicated border, exclude mask samples.
refactorings
 2019-01-02 17:26:12 +04:00
iperov f3782a012b Update Trainer.py 2019-01-01 19:50:31 +04:00
iperov cd9e2c239c Update main.py 2019-01-01 19:50:04 +04:00
iperov 64537204bb Sorry, no more linux/mac/docker support. If someone want to support it - create linux/mac fork, I will reference them in readme. 2019-01-01 19:48:03 +04:00
iperov 5c0c79e528 fix last PR 2019-01-01 19:42:19 +04:00
iperov c707fc0658 Update Trainer.py 2019-01-01 18:09:27 +04:00
iperov 46bda1d683 RecycleGAN : set minimum bs to 10 2018-12-28 23:42:05 +04:00
iperov 474fff248f RecycleGAN fixes 2018-12-28 23:13:29 +04:00
iperov 1f86d7f1dd ResNet, changed PixelShuffler to Conv2DTranspose 2018-12-28 20:38:26 +04:00
iperov f8824f9601 refactoring. Added RecycleGAN for testing. 2018-12-28 19:38:52 +04:00
iperov 8686309417 fix SubprocessorBase 2018-12-26 11:07:01 +04:00
iperov a37af3e965 remove print_on_no_embedded_data=True on sort_by_hist_dissim 2018-12-25 19:50:25 +04:00
iperov dba951412c fix DFLPNG 2018-12-25 19:49:19 +04:00