david/DeepFaceLab_Linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
418 Commits 1 Branch 0 Tags
d3ac88b79956bf5eb7b8ade4ecedc9585c9c8cd4
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
iperov d3ac88b799 fix MaskEditorTool 2019-04-05 09:32:04 +04:00
iperov de8d75b4f7 fix mask editor, 
upd manuals
 2019-04-04 22:19:56 +04:00
iperov 0fa9d269ec fixes 2019-04-04 16:34:45 +04:00
iperov 5ac7e5d7f1 changed help message for pixel loss: 
Pixel loss may help to enhance fine details and stabilize face color. Use it only if quality does not improve over time.

SAE:
previous SAE model will not work with this update.
Greatly decreased chance of model collapse.
Increased model accuracy.
Residual blocks now default and this option has been removed.
Improved 'learn mask'.
Added masked preview (switch by space key)

Converter:
fixed rct/lct in seamless mode
added mask mode (6) learned*FAN-prd*FAN-dst

added mask editor, its created for refining dataset for FANSeg model, and not for production, but you can spend your time and test it in regular fakes with face obstructions
 2019-04-04 10:22:53 +04:00
iperov 01e98cde8e upd pixel_loss help message 2019-03-31 19:21:04 +04:00
iperov 2d4773b18f _ 2019-03-31 17:24:07 +04:00
iperov 5f811a1b75 remove asking color transfer in raw mode 2019-03-31 16:48:36 +04:00
iperov 178fd070f7 Converter: fix blur region of seamless. 2019-03-31 08:52:06 +04:00
iperov c1117852d8 +imagelib.normalize_channels 2019-03-30 21:52:36 +04:00
iperov a885838363 make seamless great again! 
fixed seamless face jitter
removed options Suppress seamless jitter, seamless erode mask modifier.
seamlessed face now properly uses blur modifier
added option 'FAN-prd&dst' - using multiplied FAN prd and dst mask,
 2019-03-30 11:58:40 +04:00
iperov 13f3251ee3 converter: fixed suppress seamless jitter 2019-03-30 10:02:04 +04:00
iperov 7b5fb497f0 upd manual 2019-03-29 18:09:33 +04:00
iperov 459d72113f fix conversion speed 2019-03-29 00:18:22 +04:00
iperov 85c01e3b4a Converter: added Apply super resolution? (y/n skip:n) : , Enhance details by applying DCSCN network. 
refactorings
 2019-03-28 21:50:27 +04:00
iperov 4683c362ac changing SubpixelUpscaler to variable H,W dims, 
tensorflow backend : using depth_to_space in SubpixelUpscaler, so training speed increased by 4%
 2019-03-28 17:55:42 +04:00
iperov 689aefeb2f Converter: fix for input images with ch > 3 2019-03-28 11:12:19 +04:00
iperov 3cf3bb786e rename samples to samplelib 2019-03-27 10:44:13 +04:00
iperov 773e8d80e0 SampleGeneratorFace added ability to specify random seed (currently unused) 2019-03-27 10:39:21 +04:00
iperov 24dd4ef000 get rid of random module 2019-03-27 10:28:07 +04:00
iperov f63f78e1ab fix 2019-03-26 19:15:20 +04:00
iperov 808f74e9c8 fix 2019-03-26 19:14:30 +04:00
iperov 77d9f3c856 fix 2019-03-26 19:09:00 +04:00
iperov fedeee4395 Colab: added ability to run programs after N secs in trainer 2019-03-26 19:06:19 +04:00
iperov 009af42617 fix converter issue #205 2019-03-26 18:23:39 +04:00
iperov 070e938568 colab: final fix for preview filepath 2019-03-26 18:11:33 +04:00
iperov e8a5a4bf10 _preview.jpg for colab 2019-03-26 17:58:29 +04:00
iperov 6241c8af41 preview file for colab 2019-03-26 17:14:59 +04:00
iperov 96de328221 upd for Colab (#206) 
* changes for google colab

* 1

* 1

* 1

* 1
 2019-03-26 16:09:22 +04:00
iperov b03b147bae refactoring 2019-03-26 11:09:44 +04:00
iperov 79950c6c0e upd readme 2019-03-26 09:16:02 +04:00
iperov ec0c4d0128 upd readme 2019-03-26 09:15:22 +04:00
iperov 131b2b5c79 after save loss string now shows averaged value since last save 2019-03-25 18:14:04 +04:00
iperov bb02cc1d97 _ 2019-03-25 13:28:08 +04:00
iperov aa58d9e563 SAE: removed lightweight encoder 2019-03-25 10:05:30 +04:00
iperov addd87efa8 upd README.md 2019-03-24 19:44:09 +04:00
iperov 54239f8edf sae: optimizer mode now can be overrided 2019-03-24 16:25:30 +04:00
iperov 37505d88e3 old SAE model will not work with this update. 
Fixed bug when SAE can be collapsed during a time.

SAE: removed CA weights and encoder/decoder dims.

added new options:

Encoder dims per channel (21-85 ?:help skip:%d)
More encoder dims help to recognize more facial features, but require more VRAM. You can fine-tune model size to fit your GPU.

Decoder dims per channel (11-85 ?:help skip:%d)
More decoder dims help to get better details, but require more VRAM. You can fine-tune model size to fit your GPU.

Add residual blocks to decoder? (y/n, ?:help skip:n) :
These blocks help to get better details, but require more computing time.

Remove gray border? (y/n, ?:help skip:n) :
Removes gray border of predicted face, but requires more computing resources.
 2019-03-24 15:35:02 +04:00
iperov 4f4447d719 nnlib: implemented ReflectionPadding2D for plaidML, 
wrapping Conv2D with new padding param
 2019-03-23 22:20:05 +04:00
iperov 673d4915d9 VideoEd: added comment 2019-03-23 18:28:50 +04:00
iperov 668a3e23a1 frame extraction: fixed pixel format for PNG. Added PNG/JPG option. 2019-03-23 18:27:38 +04:00
iperov cbe2ebca7f SAE: removed random normal initialization 2019-03-23 14:57:30 +04:00
iperov 580e8250e0 fix req for new plaidml 2019-03-21 21:29:35 +04:00
iperov c4f41a7e76 Converter: added new mask modes: FAN-prd, FAN-dst 2019-03-21 21:19:03 +04:00
iperov 9849bcc1e5 fix 2019-03-21 19:04:46 +04:00
iperov 48314f74db removing dlib detector that is outdated and inaccurate 2019-03-21 19:00:42 +04:00
iperov 565af4d1da refactoring 2019-03-21 18:58:38 +04:00
iperov af1760b22d plaidML: upgrading version 2019-03-21 18:57:02 +04:00
iperov 7a0cc56603 extractor: fixes, optimizations, 
manual extractor: added 'a' option to switch accuracy mode
 2019-03-21 18:56:32 +04:00
iperov 63c9be3d1f fix 2019-03-21 12:15:04 +04:00
iperov d1676dea06 refactorings, optimizations 2019-03-21 11:58:54 +04:00
iperov 97008291b8 fix 2019-03-20 14:43:02 +04:00
iperov 6169e6ba8a fix fanseg 2019-03-20 09:08:42 +04:00
iperov a3df04999c removing trailing spaces 2019-03-19 23:53:27 +04:00
iperov fa4e579b95 fix fanseg 2019-03-19 23:49:41 +04:00
iperov 034ad3cce5 upd fan segmentator 2019-03-19 19:44:14 +04:00
iperov 1f569117c8 accurate landmark extractor now by default 2019-03-19 14:01:15 +04:00
iperov a0c1ce3e7e final sort: increased speed 2019-03-19 13:45:26 +04:00
iperov 33606e327b fixed landmark extraction of face with opened mouth 2019-03-19 00:23:52 +04:00
iperov 7c1ea1a617 removing dflimg image_to_face_mat 2019-03-18 14:42:10 +04:00
iperov 5d819e3e83 upd manual_ru 2019-03-18 11:49:01 +04:00
iperov 00c6a0cdaf accurate landmarks extraction now as an option 2019-03-18 11:24:41 +04:00
iperov bf831331e6 fix 2019-03-18 10:58:03 +04:00
iperov da7cf225db fix 2019-03-18 10:38:48 +04:00
iperov b8efb4cbba enhancing landmarks extractor by using s3fd second pass inside second pass, 
it will be x2 slower, but time will be saved due to more images will be marked properly
works on 2GB+
 2019-03-18 10:25:24 +04:00
iperov 1d56585f33 fix ability for auto re-extract dst faces, after this update DFL torrent extractor scripts will not work. 2019-03-18 01:12:04 +04:00
iperov b03d62a29b extractor: added ability to re-extract dst faces with transferring all necessary meta data 2019-03-18 00:43:07 +04:00
iperov 00e56299c4 S3FD: wrong small face check fix 2019-03-18 00:30:08 +04:00
iperov 2b40fa182f fix 2019-03-17 23:50:18 +04:00
iperov a71defc69a removing fail solutions 2019-03-17 23:47:14 +04:00
iperov c311f09fa4 _ 2019-03-17 21:14:24 +04:00
iperov 73e91cc0b5 upd LandmarksProcessor.py 2019-03-17 21:14:05 +04:00
iperov 7aebfa3f7f added AdaBound 2019-03-17 19:17:44 +04:00
iperov a7bec17a34 _ 2019-03-17 16:24:36 +04:00
iperov d71a310fd7 SAE: forgot to remove normalizing from tanh 2019-03-17 13:03:49 +04:00
iperov 4ff88865ce refactoring 2019-03-16 21:29:56 +04:00
iperov f009edae79 FANSegmentator for developing 2019-03-16 20:58:20 +04:00
iperov 1c8845d558 model fansegmentator for developing purposes 2019-03-16 20:57:51 +04:00
iperov f3b343c0e5 small fixed and refactorings 2019-03-16 20:55:51 +04:00
iperov d6a45763a2 SAE: added option "Use CA weights": 
Initialize network with 'Convolution Aware' weights. This may help to achieve a higher accuracy model, but consumes time at first run.
 2019-03-16 12:54:36 +04:00
iperov 71ff0ce1a7 nothing interesting 2019-03-16 09:22:00 +04:00
iperov 7c66503382 sorter: fix final sort 2019-03-16 09:20:55 +04:00
iperov 5076feb90f SAE: revert back to sigmoid. Trainings must be restarted. 2019-03-16 09:01:11 +04:00
iperov ea5fe28d08 fix final sorter 2019-03-15 23:41:34 +04:00
iperov a8c987fa0f fix performance issue 2019-03-15 11:50:13 +04:00
iperov 4ffae1a954 fix performance issue 2019-03-15 11:48:38 +04:00
iperov 3549272244 fix for final 2019-03-15 11:03:37 +04:00
iperov 1beb2f07f0 fix get_image_hull_mask 2019-03-14 15:43:10 +04:00
iperov 9823421a44 added transparent mask to draw_landmarks 2019-03-14 12:16:21 +04:00
iperov 5bd3f875fa fix 2019-03-14 10:50:53 +04:00
iperov 6e59f1a150 Sorter: new better blur estimator 2019-03-14 10:38:56 +04:00
iperov 296e8a111a fix for Linux 2019-03-14 05:08:15 +04:00
iperov 62af1b6f16 S3FD : filtering faces < 40pix. 2019-03-14 01:23:39 +04:00
iperov 8da47fec13 fix ModelBase, nnlib 2019-03-13 20:53:59 +04:00
iperov da0fc2d2e1 update manual_ru 2019-03-13 20:03:46 +04:00
iperov 3375088669 SAE: optimizer_mode option now cannot be overridden by restart 2019-03-13 20:00:16 +04:00
iperov a9026ccb67 fix ModelBase, nnlib 2019-03-13 19:50:16 +04:00
iperov 90a7d4b1e7 fix force_plaidML 2019-03-13 18:30:40 +04:00
iperov 58763756f5 SAE: removed simple_optimizer . Added optimizer mode for tensorflow only (NVIDIA cards), allows to train x2-x3 bigger networks with normal Adam optimizer, consuming VRAM and CPU power. 2019-03-13 11:54:17 +04:00
iperov 3c6775bae7 fix ModelBase.py 2019-03-12 23:22:58 +04:00
iperov aaf7ecd595 update manual_ru 2019-03-12 21:27:37 +04:00