david/DeepFaceLab_Linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
556 Commits 1 Branch 0 Tags
96d0e3fbee8f11dee78d9f609ce3a98a6ed8d2a0
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
iperov 96d0e3fbee converter output filename - fixed indexing, now starts from 00001 as extracted frames 2019-08-26 10:39:04 +04:00
iperov 029cabea3d minor fix 2019-08-26 10:03:10 +04:00
iperov d3eadbf5f3 upd readme 2019-08-26 09:51:32 +04:00
iperov 6243190f74 fix help screen 2019-08-26 08:14:31 +04:00
iperov 25da22fdc9 minor fix 2019-08-25 22:32:21 +04:00
iperov 63d30c49ae fixes and optimizations, 
converters: added new option sharpen_mode and sharpen_amount
 2019-08-25 19:18:51 +04:00
iperov c39ed9d9c9 updated pdf manuals for AVATAR model. 
Avatar converter: added super resolution option.
All converters: super resolution DCSCN network is now replaced by RankSRGAN
 2019-08-25 17:43:52 +04:00
iperov 19c66286da fix gen_warp_params now accepts any square images 2019-08-25 14:06:33 +04:00
iperov 6c66495bcf default avatar type option is now HEAD. Head produces stable result. 2019-08-25 08:16:54 +04:00
iperov d129b5dd7f sort data for CAInitializerMP 2019-08-25 07:50:27 +04:00
iperov 00dce38187 fix 2019-08-25 07:43:22 +04:00
iperov b572b8f4d4 fix ConverterConfig 2019-08-25 00:30:05 +04:00
iperov e3505d9b8c fix AVATARModel 2019-08-24 20:33:29 +04:00
iperov 5968ac21f6 fix AVATARModel 2019-08-24 19:55:38 +04:00
iperov 2a9a579436 fix 2019-08-24 13:23:15 +04:00
iperov 407ce3b1ca Added interactive converter. 
With interactive converter you can change any parameter of any frame and see the result in real time.

Converter: added motion_blur_power param.
Motion blur is applied by precomputed motion vectors.
So the moving face will look more realistic.

RecycleGAN model is removed.

Added experimental AVATAR model. Minimum required VRAM is 6GB (NVIDIA), 12GB (AMD)
Usage:
1) place data_src.mp4 10-20min square resolution video of news reporter sitting at the table with static background,
   other faces should not appear in frames.
2) process "extract images from video data_src.bat" with FULL fps
3) place data_dst.mp4 video of face who will control the src face
4) process "extract images from video data_dst FULL FPS.bat"
5) process "data_src mark faces S3FD best GPU.bat"
6) process "data_dst extract unaligned faces S3FD best GPU.bat"
7) train AVATAR.bat stage 1, tune batch size to maximum for your card (32 for 6GB), train to 50k+ iters.
8) train AVATAR.bat stage 2, tune batch size to maximum for your card (4 for 6GB), train to decent sharpness.
9) convert AVATAR.bat
10) converted to mp4.bat

updated versions of modules
 2019-08-24 12:57:29 +04:00
iperov 3f0bf2e994 upd readme 2019-08-20 17:11:37 +04:00
iperov 4058f51c02 Merge branch 'master' of https://github.com/iperov/DeepFaceLab 2019-08-20 17:10:31 +04:00
iperov fc5efb559d upd readme 2019-08-20 17:10:00 +04:00
iperov d16759bcd3 ConverterMasked: added mask gradient of bottom area, same as side gradient 2019-08-11 13:22:01 +04:00
iperov e8c5f168bd Merge branch 'master' of https://github.com/iperov/DeepFaceLab 2019-08-11 11:17:38 +04:00
iperov b72d5a3f9a fixed error "Failed to get convolution algorithm" on some systems 
fixed error "dll load failed" on some systems
Expanded eyebrows line of face masks. It does not affect mask of FAN-x converter mode.
 2019-08-11 11:17:22 +04:00
Colombo d886cd79a8 upd readme 2019-07-15 15:27:51 +04:00
iperov 8484060e01 Trainer: added option for all models 
Enable autobackup? (y/n ?:help skip:%s) :
Autobackup model files with preview every hour for last 15 hours. Latest backup located in model/<>_autobackups/01

SAE: added option only for CUDA builds:
Enable gradient clipping? (y/n, ?:help skip:%s) :
Gradient clipping reduces chance of model collapse, sacrificing speed of training.
 2019-06-20 10:42:55 +04:00
iperov fb9fd8c2b9 Update README.md 2019-06-19 12:24:11 +04:00
iperov 3d29130d5c closing the repo 2019-06-13 08:38:09 +04:00
iperov ab8d03b4bb fix 2019-06-02 19:20:06 +04:00
iperov c9da4cd89b fix for plaidML 2019-05-24 09:30:39 +04:00
iperov 3114ae9d7b upd plaidml ver 2019-05-20 22:42:34 +04:00
iperov 480360ba10 upd 2019-05-18 23:43:40 +04:00
iperov 06831517f5 upd 2019-05-15 08:03:50 +04:00
iperov 7be97af845 upd paypal link 2019-05-15 07:58:40 +04:00
iperov 66a12a973a fix choosing preview image on options override 2019-05-14 17:00:25 +04:00
iperov d6e8dde481 'sort by yaw' option now can be overriden each run 2019-05-14 09:33:53 +04:00
iperov 615a999c68 added google drive download link 2019-05-14 09:33:10 +04:00
iperov b04e9e77e2 upd doc 2019-05-12 07:59:35 +04:00
iperov 444bf699f7 back to 100 chance of random_ct 2019-05-11 21:20:02 +04:00
iperov 28af2f41ec fix 2019-05-11 19:49:02 +04:00
iperov 22efba57a3 fix 2019-05-11 19:44:01 +04:00
iperov 1493551410 fix 2019-05-11 19:42:03 +04:00
iperov 8d7edd172c random_ct_sample - now not applying with 20% chance 2019-05-11 19:40:02 +04:00
iperov 8294feca24 extractior: fix extract from already extracted dflimg 2019-05-11 17:36:22 +04:00
iperov 53c4f8a86e cleaning 2019-05-11 16:55:06 +04:00
iperov 39809ff7dc upd 2019-05-11 16:15:16 +04:00
iperov 2239c8d9ab upd readme 2019-05-11 12:18:43 +04:00
iperov 6143962248 SAE: option apply_random_ct now True by default 2019-05-10 19:50:19 +04:00
iperov e8f207557b fix bgr_shuffle 2019-05-10 08:11:17 +04:00
iperov 5a9498543d refactoring 2019-05-09 18:05:50 +04:00
iperov d2011f8c32 upd doc 2019-05-08 09:32:32 +04:00
iperov 3555801046 upd docs 2019-05-07 13:09:20 +04:00
iperov d003366033 cleaning 2019-05-07 10:47:51 +04:00
iperov d8c1e2e58b change help for apply_random_ct option 2019-05-07 10:47:29 +04:00
iperov 809cc14860 fix 2019-05-06 16:27:18 +04:00
iperov d9c2e96f01 fix 2019-05-06 12:52:47 +04:00
iperov a805f81142 SAE: added test option: 'Apply random color transfer to src faceset' 2019-05-06 11:34:56 +04:00
iperov bde700243c fix for plaidML 2019-05-05 19:22:26 +04:00
iperov 35ab63f752 add launch prog by timer repeatedly for colab 2019-05-05 17:05:03 +04:00
iperov b50220a7d1 upd doc 2019-05-03 08:54:07 +04:00
iperov 37ca4281f3 _ 2019-05-02 09:27:28 +04:00
iperov f26267fddf sae: upd help 2019-05-02 09:06:22 +04:00
iperov 54fa75aa13 fix 2019-05-02 00:39:18 +04:00
iperov 6dc1d43fe9 fix 2019-05-01 20:03:15 +04:00
iperov 9577c2d254 fix 2019-05-01 19:59:43 +04:00
iperov 2a8dd788dc SAE: added option 'Pretrain the model?', 
Pretrain the model with large amount of various faces. This technique may help to train the fake with overly different face shapes and light conditions of src/dst data. Face will be look more like a morphed. To reduce the morph effect, some model files will be initialized but not be updated after pretrain: LIAE: inter_AB.h5 DF: both decoders.h5. The longer you pretrain the model the more morphed face will look. After that, save and run the training again.
 2019-05-01 19:55:27 +04:00
iperov 659aa5705a _ 2019-04-30 17:14:02 +04:00
iperov 1f1f94848b cleaning 2019-04-30 07:46:49 +04:00
iperov efb22ecce0 5 secs for override settings for colab 2019-04-30 07:32:15 +04:00
iperov b16c745f1f upd manuals 2019-04-29 08:34:04 +04:00
iperov 5eaf3eb500 fix 3rd pass extractor hang on AMD 8+ core processors 2019-04-28 23:40:26 +04:00
iperov 2cd028fb67 _ 2019-04-28 21:16:27 +04:00
iperov 7140ee8684 Converter: fixed degrade color power after 'lct' 2019-04-28 19:34:56 +04:00
iperov ab714dfbfe _ 2019-04-28 16:29:32 +04:00
iperov 7c50003ec7 fix 2019-04-28 15:13:12 +04:00
iperov 35e1bceeb4 update numpy ver 2019-04-27 18:37:46 +04:00
iperov 836693d64f added option 'Choose image for the preview history? (y/n skip:' 2019-04-27 10:03:54 +04:00
iperov 9e05e58ac4 _ 2019-04-26 21:43:43 +04:00
iperov f89200d236 nothing interesting 2019-04-26 15:18:48 +04:00
iperov 0e088f6415 _ 2019-04-25 14:46:39 +04:00
iperov c0a63addd4 SampleGeneratorFace optimizations 2019-04-24 21:27:05 +04:00
iperov 9535a657d2 SAE: revert back CA weights option 2019-04-24 13:44:12 +04:00
iperov 0cd8dd7296 upd comment 2019-04-24 11:41:10 +04:00
iperov b6711b97a3 SAE added CA weights 2019-04-24 11:38:45 +04:00
iperov 60ed56a801 upd dev_poseestimator 2019-04-24 11:33:11 +04:00
iperov 947feac047 refactorings 2019-04-24 11:28:58 +04:00
iperov e1da9c56b4 SAE collapse fix (#245) 
* test

* _

* _

* upd dev_poseest

* SAE: finally collapses are fixed

* fix batch size help
 2019-04-24 09:38:26 +04:00
iperov d62785ca5a _ 2019-04-24 00:36:09 +04:00
iperov 33a45ec531 revert docs 2019-04-23 18:36:40 +04:00
iperov 747e39145e _ 2019-04-23 18:34:00 +04:00
iperov ea7ec74721 change help for batch size 2019-04-23 18:31:12 +04:00
iperov 385d5dabbf remove df-s and liae-s 2019-04-23 18:28:17 +04:00
iperov 2809d495c2 _ 2019-04-23 17:31:58 +04:00
iperov 268b402513 _ 2019-04-23 17:03:53 +04:00
iperov 47f9bad42b SAE: df-s liae-s archis 2019-04-23 17:03:30 +04:00
iperov 8969e80275 _ 2019-04-23 14:07:38 +04:00
iperov 565c131b97 SAE: removed option 'remove gray border', because it makes the model very resource intensive 2019-04-23 08:31:13 +04:00
iperov 832ea90a5f missing file 2019-04-23 08:20:43 +04:00
iperov e58197ca22 initial code to extract umdfaces.io dataset and train pose estimator 2019-04-23 08:14:09 +04:00
iperov 51a917facc back to 100* loss 2019-04-22 10:42:17 +04:00
iperov cd2767cca0 SAE: back to batchnormalization 2019-04-22 10:28:01 +04:00
iperov 3aef9a507b fix 2019-04-22 00:52:16 +04:00