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
93ee889597
Identity is not the same thing as equality in Python ( #291 )
...
Use ==/!= to compare str, bytes, and int literals
$ python
```python
>>> method = 'Mi'
>>> method += 'n'
>>> method == 'Min'
True
>>> method is 'Min'
False
```
2019-06-27 21:10:22 +04:00
659aa5705a
_
2019-04-30 17:14:02 +04:00
2cd028fb67
_
2019-04-28 21:16:27 +04:00
ab714dfbfe
_
2019-04-28 16:29:32 +04:00
f89200d236
nothing interesting
2019-04-26 15:18:48 +04:00
0e088f6415
_
2019-04-25 14:46:39 +04:00
9535a657d2
SAE: revert back CA weights option
2019-04-24 13:44:12 +04:00
60ed56a801
upd dev_poseestimator
2019-04-24 11:33:11 +04:00
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
2809d495c2
_
2019-04-23 17:31:58 +04:00
268b402513
_
2019-04-23 17:03:53 +04:00
565c131b97
SAE: removed option 'remove gray border', because it makes the model very resource intensive
2019-04-23 08:31:13 +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
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
b03b147bae
refactoring
2019-03-26 11:09:44 +04:00
bb02cc1d97
_
2019-03-25 13:28:08 +04:00
c4f41a7e76
Converter: added new mask modes: FAN-prd, FAN-dst
2019-03-21 21:19:03 +04:00
7a0cc56603
extractor: fixes, optimizations,
...
manual extractor: added 'a' option to switch accuracy mode
2019-03-21 18:56:32 +04:00
63c9be3d1f
fix
2019-03-21 12:15:04 +04:00
d1676dea06
refactorings, optimizations
2019-03-21 11:58:54 +04:00
6169e6ba8a
fix fanseg
2019-03-20 09:08:42 +04:00
a3df04999c
removing trailing spaces
2019-03-19 23:53:27 +04:00
fa4e579b95
fix fanseg
2019-03-19 23:49:41 +04:00
034ad3cce5
upd fan segmentator
2019-03-19 19:44:14 +04:00
33606e327b
fixed landmark extraction of face with opened mouth
2019-03-19 00:23:52 +04:00
da7cf225db
fix
2019-03-18 10:38:48 +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
00e56299c4
S3FD: wrong small face check fix
2019-03-18 00:30:08 +04:00
c311f09fa4
_
2019-03-17 21:14:24 +04:00
73e91cc0b5
upd LandmarksProcessor.py
2019-03-17 21:14:05 +04:00
a7bec17a34
_
2019-03-17 16:24:36 +04:00
f009edae79
FANSegmentator for developing
2019-03-16 20:58:20 +04:00
f3b343c0e5
small fixed and refactorings
2019-03-16 20:55:51 +04:00
1beb2f07f0
fix get_image_hull_mask
2019-03-14 15:43:10 +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
e50dc0d748
2DFAN-4: fix bug
2019-03-11 10:26:03 +04:00
893354b870
fix S3FD for plaidML, fix S3FD warnings on Lambda layers.
2019-03-11 09:32:00 +04:00
338a8fccc6
added missing file
2019-03-10 23:41:02 +04:00
fbf39d2727
added new extractor: S3FD,
...
all extractors now produce less false-positive faces
2019-03-10 23:18:10 +04:00
0cc251a9ab
2nd pass of extractor : speed significantly increased
2019-03-08 16:05:24 +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
2019-02-28 11:56:31 +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
2019-02-19 17:33:12 +04:00
6e12594af1
added util --add-landmarks-debug-images
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
2019-02-12 21:31:37 +04:00
bda3fb3da1
refactoring
2019-02-10 21:40:58 +04:00
b6c4171ea1
optimizations of nnlib and SampleGeneratorFace,
...
refactorings
2019-01-22 11:52:04 +04:00
iperov