76ca79216e
Upgraded to TF version 1.13.2
...
Removed the wait at first launch for most graphics cards.
Increased speed of training by 10-20%, but you have to retrain all models from scratch.
SAEHD:
added option 'use float16'
Experimental option. Reduces the model size by half.
Increases the speed of training.
Decreases the accuracy of the model.
The model may collapse or not train.
Model may not learn the mask in large resolutions.
true_face_training option is replaced by
"True face power". 0.0000 .. 1.0
Experimental option. Discriminates the result face to be more like the src face. Higher value - stronger discrimination.
Comparison - https://i.imgur.com/czScS9q.png
2020-01-25 21:58:19 +04:00
0ce96875a1
1
2020-01-22 18:49:32 +04:00
60804ca3ba
1
2020-01-22 13:41:05 +04:00
38b85108b3
DFL-2.0 initial branch commit
2020-01-21 18:43:39 +04:00
4e67278c66
fix 0 faces detected in manual extractor
2019-12-28 16:45:40 +04:00
7174dc835a
fixes
2019-12-22 21:44:28 +04:00
dd45b7dacc
cleaning
2019-12-22 15:02:53 +04:00
8153e90ba3
refactoring
2019-12-22 14:05:41 +04:00
9312a3c334
Extractor: 2nd pass now faster on frames where faces are not found
2019-12-22 10:46:44 +04:00
28b948888c
fix extractor for some systems
2019-12-17 09:52:48 +04:00
1bfd65abe5
extractor for AMD gpu: increase no response time
2019-11-24 19:37:21 +04:00
6b14741160
1
2019-11-21 11:40:55 +04:00
668513a507
1
2019-11-16 16:54:10 +04:00
f6f8f8ee5d
change default jpg face extractor quality to 100
2019-11-11 09:13:42 +04:00
71a98e2ee4
compatibility fix
2019-11-04 02:01:28 +04:00
410b8e98a0
fix manual extractor
2019-10-27 18:53:01 +04:00
75eeef0a96
fix for amd
2019-10-24 21:59:13 +04:00
0d3b25812d
fix
2019-10-20 18:02:23 +04:00
85cbdcd290
revert fix "face could be detected twice"
2019-10-14 19:11:49 +04:00
1de1e0029f
Extractor now produces a less shaked face. but second pass is now slower by 25%,
...
before/after: https://imgur.com/L77puLH
2019-10-14 12:09:32 +04:00
e013cb0f6b
moving some files
2019-10-14 09:34:44 +04:00
2b264da86b
fixed bug when same face can be detected twice
2019-10-13 14:59:50 +04:00
63ecd4ec34
speed up S3FD extraction for GPU with >= 11GB vram
2019-10-10 13:22:14 +04:00
d9d10f91c2
S3FD and 2DFAN-4 were improperly ported from pytorch. now fixed.
2019-09-20 17:16:37 +04:00
dc11ec32be
SAE : WARNING, RETRAIN IS REQUIRED !
...
fixed model sizes from previous update.
avoided bug in ML framework(keras) that forces to train the model on random noise.
Converter: added blur on the same keys as sharpness
Added new model 'TrueFace'. This is a GAN model ported from https://github.com/NVlabs/FUNIT
Model produces near zero morphing and high detail face.
Model has higher failure rate than other models.
Keep src and dst faceset in same lighting conditions.
2019-09-19 11:13:56 +04:00
faa14c4e59
fix extractor error on load grayscale images
2019-09-06 11:54:49 +04:00
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
8294feca24
extractior: fix extract from already extracted dflimg
2019-05-11 17:36:22 +04:00
e58197ca22
initial code to extract umdfaces.io dataset and train pose estimator
2019-04-23 08:14:09 +04:00
046649e6be
update == 04.20.2019 == ( #242 )
...
* superb improved fanseg
* _
* _
* added FANseg extractor for src and dst faces to use it in training
* -
* _
* _
* update to 'partial' func
* _
* trained FANSeg_256_full_face.h5,
new experimental models: AVATAR, RecycleGAN
* _
* _
* _
* fix for TCC mode cards(tesla), was conflict with plaidML initialization.
* _
* update manuals
* _
2019-04-20 08:23:08 +04:00
9f68b25987
Extractor: added warning messages if aligned folder contains files that will be deleted.
2019-04-06 10:01:59 +04:00
de8d75b4f7
fix mask editor,
...
upd manuals
2019-04-04 22:19:56 +04:00
b03b147bae
refactoring
2019-03-26 11:09:44 +04:00
7a0cc56603
extractor: fixes, optimizations,
...
manual extractor: added 'a' option to switch accuracy mode
2019-03-21 18:56:32 +04:00
d1676dea06
refactorings, optimizations
2019-03-21 11:58:54 +04:00
a3df04999c
removing trailing spaces
2019-03-19 23:53:27 +04:00
1f569117c8
accurate landmark extractor now by default
2019-03-19 14:01:15 +04:00
7c1ea1a617
removing dflimg image_to_face_mat
2019-03-18 14:42:10 +04:00
00c6a0cdaf
accurate landmarks extraction now as an option
2019-03-18 11:24:41 +04:00
bf831331e6
fix
2019-03-18 10:58:03 +04:00
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
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
b03d62a29b
extractor: added ability to re-extract dst faces with transferring all necessary meta data
2019-03-18 00:43:07 +04:00
4ff88865ce
refactoring
2019-03-16 21:29:56 +04:00
f3b343c0e5
small fixed and refactorings
2019-03-16 20:55:51 +04:00
9823421a44
added transparent mask to draw_landmarks
2019-03-14 12:16:21 +04:00
62af1b6f16
S3FD : filtering faces < 40pix.
2019-03-14 01:23:39 +04:00
893354b870
fix S3FD for plaidML, fix S3FD warnings on Lambda layers.
2019-03-11 09:32:00 +04:00
fbf39d2727
added new extractor: S3FD,
...
all extractors now produce less false-positive faces
2019-03-10 23:18:10 +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
2019-03-08 17:01:11 +04:00
Colombo
