github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-03-12 20:42:45 -07:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • aaf7ecd595 update manual_ru iperov 2019-03-12 21:27:37 +04:00
  • 97b6fabaab change 'epoch' to 'iter', added timestamp prefix to training string iperov 2019-03-12 19:23:52 +04:00
  • 69174a48e0 fix DFLOptimizer iperov 2019-03-12 16:56:59 +04:00
  • 46ff33bf89 SAE: dssim kernel size now depends on resolution iperov 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 iperov 2019-03-12 09:32:35 +04:00
  • 3bad8dd8ec fix iperov 2019-03-11 21:53:28 +04:00
  • ee8dbcbc35 revert back Adam iperov 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 iperov 2019-03-11 18:23:01 +04:00
  • e50dc0d748 2DFAN-4: fix bug iperov 2019-03-11 10:26:03 +04:00
  • 52f149a570 update manual_ru iperov 2019-03-11 09:34:47 +04:00
  • 893354b870 fix S3FD for plaidML, fix S3FD warnings on Lambda layers. iperov 2019-03-11 09:32:00 +04:00
  • 338a8fccc6 added missing file iperov 2019-03-10 23:41:02 +04:00
  • fbf39d2727 added new extractor: S3FD, all extractors now produce less false-positive faces iperov 2019-03-10 23:18:10 +04:00
  • 9440224556 change TF console log level to 'errors only' iperov 2019-03-09 20:23:33 +04:00
  • 95e70d510f upd doc_prebuilt_windows_app.md iperov 2019-03-09 10:09:27 +04:00
  • f2de3b5ab7 upd manual_ru iperov 2019-03-09 10:02:14 +04:00
  • 9cc1a20255 update manual_ru iperov 2019-03-08 20:15:00 +04:00
  • 168d48b119 extractor: increased speed of 1st pass by DLIB for >= 4GB vram cards, added 'h' key for hide the help in manual extractor iperov 2019-03-08 17:01:11 +04:00
  • bced4d3259 - iperov 2019-03-08 16:39:27 +04:00
  • 0cc251a9ab 2nd pass of extractor : speed significantly increased iperov 2019-03-08 16:05:24 +04:00
  • 8f7b268376 upd manual_ru iperov 2019-03-07 20:51:37 +04:00
  • e625cfef0b upd doc/doc_prebuilt_windows_app.md iperov 2019-03-07 20:39:53 +04:00
  • 5587c93e01 fix ConverterMasked.py, changing requirements changing device.py ENV vars iperov 2019-03-07 19:48:12 +04:00
  • c3eea0cf98 upd device.py iperov 2019-03-04 11:17:08 +04:00
  • bdb45357ee rename requirements-AVX-cuda10.0-cudnn7.4.1.txt iperov 2019-03-04 10:58:52 +04:00
  • 6094e5ead8 added Util.recover_original_aligned_filename iperov 2019-03-04 10:57:44 +04:00
  • ae4b6e6271 add requirements-SSE-cuda9.0-cudnn7.1.4.txt iperov 2019-03-04 09:49:40 +04:00
  • 26741f3376 upd set_process_lowest_prio() iperov 2019-03-03 21:59:28 +04:00
  • 69af01d871 update set_process_lowest_prio() iperov 2019-03-03 21:59:10 +04:00
  • 714d4f0fca small fix iperov 2019-03-03 16:42:13 +04:00
  • 42adbd94e7 upd ConverterMasked.py iperov 2019-03-03 16:06:01 +04:00
  • 0448220f8f update manual_ru iperov 2019-03-03 15:53:36 +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 iperov 2019-03-03 15:33:52 +04:00
  • 87236921a5 fix VideoEd.py iperov 2019-03-02 18:06:06 +04:00
  • 1d52e665f8 fix VideoEd.py iperov 2019-03-02 18:02:00 +04:00
  • 18d2c52d8c added manual_ru.pdf iperov 2019-03-02 17:40:27 +04:00
  • 4196e962a8 added VideoEd - operating video files by ffmpeg from python. iperov 2019-03-02 14:58:22 +04:00
  • e0907423a9 nothing interesting iperov 2019-03-01 08:18:26 +04:00
  • 847622ee3a converter: fix seamless iperov 2019-02-28 23:12:24 +04:00
  • 18d5829015 Converter: fix jitter of seamless mode iperov 2019-02-28 21:27:37 +04:00
  • 7cea93c0f2 nothing interesting iperov 2019-02-28 20:10:58 +04:00
  • 46f4d6c426 fix cpu fallback for extractor iperov 2019-02-28 14:54:59 +04:00
  • 8f2e69ab27 upgrading to cuda 10.0, cudnn 7.4.1, tf 1.13.1, dlib 19.16.0 iperov 2019-02-28 13:39:54 +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 iperov 2019-02-28 11:56:31 +04:00
  • 7db469a1da fix nnlib/device.py for some notebooks iperov 2019-02-25 21:34:47 +04:00
  • ac5ac75645 nnlib added force_has_nvidia_device iperov 2019-02-25 21:15:58 +04:00
  • 281787ac3e - iperov 2019-02-22 23:25:01 +04:00
  • daebe10ca7 Extractor: fix aspect ratio for square images, now we can re-extract face manually from already aligned jpg image without quality loss. iperov 2019-02-22 17:28:08 +04:00
  • 5bbd8997d9 fix Sorter.py iperov 2019-02-22 15:22:42 +04:00
  • 5e474c3462 added sort by one face in images. it trashes all images in which more than 1 face is found iperov 2019-02-22 11:32:27 +04:00
  • 65752e044b SAE: added support 64-256 resolution multiple of 16 iperov 2019-02-21 20:44:55 +04:00
  • a858732b1d refactoring iperov 2019-02-21 20:06:04 +04:00
  • 97685ce0ae added saving model_summary.txt iperov 2019-02-21 19:55:44 +04:00
  • f0a20b46d3 SAE: added new archi 'vg' iperov 2019-02-21 17:53:59 +04:00
  • d66829aae4 proper nnlib.dssim iperov 2019-02-20 19:03:49 +04:00
  • cd4e5b9ba6 Fixed typo (#156) andy-ger 2019-02-20 15:12:30 +01:00
  • 497e17b595 upd readme iperov 2019-02-19 21:46:19 +04:00
  • d29b8fd469 update readme iperov 2019-02-19 21:45:40 +04:00
  • b939fe9d85 OpenCL support: fix bug, adding new requirements files iperov 2019-02-19 20:48:39 +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 iperov 2019-02-19 17:33:12 +04:00
  • 3a9d450281 little fix iperov 2019-02-16 21:14:15 +04:00
  • 642b88a8d3 upd doc/doc_sort_tool.md iperov 2019-02-15 20:09:51 +04:00
  • 22ccec7036 Clean language up docs (#147) TooMuchFun 2019-02-15 08:06:13 -08:00
  • 72c7db4980 trainer preview: added [l]: change history range iperov 2019-02-15 19:27:44 +04:00
  • 75eb7468ee ConverterMasked: better lct iperov 2019-02-14 18:43:24 +04:00
  • fbf6b5f25e upd readme iperov 2019-02-13 21:24:55 +04:00
  • 43d0282995 upd README.md iperov 2019-02-13 21:10:29 +04:00
  • 58991dd22f update DeepFaceLab_convertor_overview iperov 2019-02-13 17:32:30 +04:00
  • e759575060 update DeepFaceLab_convertor_overview iperov 2019-02-13 17:29:26 +04:00
  • 2bd983703e ConverterMasked: removed default transfercolor, added Apply color transfer to predicted face - modes rct / lct iperov 2019-02-13 16:27:57 +04:00
  • 218a5cfd05 upd doc_ready_to_work_facesets.md iperov 2019-02-13 13:45:14 +04:00
  • 5a727f4e50 fix manual extractor bugs iperov 2019-02-13 11:02:12 +04:00
  • 6e12594af1 added util --add-landmarks-debug-images iperov 2019-02-13 10:17:08 +04:00
  • 06fe1314d8 removing default yaw_value from DFLIMG files, added better pitch/yaw estimator from 68 landmarks, improving face yaw accuracy for sorting and trainers, added sort by face-pitch iperov 2019-02-12 21:31:37 +04:00
  • 535041f7bb upd iperov 2019-02-12 10:55:41 +04:00
  • 429e7e6aee upd nnlib.py iperov 2019-02-12 09:30:38 +04:00
  • e9313e29f6 update doc_tips_and_tricks.md iperov 2019-02-11 22:10:31 +04:00
  • e38c970e45 upd README.md iperov 2019-02-11 21:51:53 +04:00
  • 900aaa8894 upd README.md iperov 2019-02-11 21:47:28 +04:00
  • e069b839f1 upd readme iperov 2019-02-11 21:46:51 +04:00
  • d8833e929e upd nnlib.py iperov 2019-02-11 21:29:30 +04:00
  • 6c944d8989 upd readme iperov 2019-02-11 21:26:51 +04:00
  • 4ffb74fb79 upd some help in models iperov 2019-02-11 17:20:13 +04:00
  • 470fb9287a SAE: remove rare sample booster. DSSIM->MSE transition now between 5-20k epochs. iperov 2019-02-11 17:18:01 +04:00
  • f8e63970d2 H64, H128, DF, LIAEF128: added pixel loss option. iperov 2019-02-11 12:05:54 +04:00
  • af3dd59f67 SAE: remove multiscale decoder option, default - true iperov 2019-02-11 10:36:02 +04:00
  • e5995630fc fix iperov 2019-02-10 23:00:08 +04:00
  • 0866b2c509 manual extractor: added zoom for small faces iperov 2019-02-10 22:40:57 +04:00
  • bda3fb3da1 refactoring iperov 2019-02-10 21:40:58 +04:00
  • 854ab11de3 fix bug with samples that were not clipped after tanh-untanh transformations, upd README.md iperov 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 iperov 2019-02-09 20:33:26 +04:00
  • b87e6be614 upd README.md iperov 2019-02-09 19:35:31 +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 iperov 2019-02-09 18:53:37 +04:00
  • f93b4713a9 upd README.md iperov 2019-02-09 11:04:37 +04:00
  • 797336d8c0 upd README.md iperov 2019-02-08 09:09:50 +04:00
  • ea7c65c4e5 upd ModelBase.py iperov 2019-02-07 22:38:31 +04:00
  • a65b557b0e loss history with epoch now saves to preview history images iperov 2019-02-07 22:34:51 +04:00
  • 9545774c59 upd README.md iperov 2019-02-07 21:59:52 +04:00
  • e5823097d5 upd rea iperov 2019-02-07 19:44:48 +04:00
  • a250f03663 upd README.md iperov 2019-02-07 19:42:58 +04:00