66a12a973a
fix choosing preview image on options override
2019-05-14 17:00:25 +04:00
d6e8dde481
'sort by yaw' option now can be overriden each run
2019-05-14 09:33:53 +04:00
39809ff7dc
upd
2019-05-11 16:15:16 +04:00
6143962248
SAE: option apply_random_ct now True by default
2019-05-10 19:50:19 +04:00
5a9498543d
refactoring
2019-05-09 18:05:50 +04:00
d2011f8c32
upd doc
2019-05-08 09:32:32 +04:00
d8c1e2e58b
change help for apply_random_ct option
2019-05-07 10:47:29 +04:00
a805f81142
SAE: added test option: 'Apply random color transfer to src faceset'
2019-05-06 11:34:56 +04:00
f26267fddf
sae: upd help
2019-05-02 09:06:22 +04:00
54fa75aa13
fix
2019-05-02 00:39:18 +04:00
6dc1d43fe9
fix
2019-05-01 20:03:15 +04:00
9577c2d254
fix
2019-05-01 19:59:43 +04:00
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
659aa5705a
_
2019-04-30 17:14:02 +04:00
efb22ecce0
5 secs for override settings for colab
2019-04-30 07:32:15 +04:00
2cd028fb67
_
2019-04-28 21:16:27 +04:00
836693d64f
added option 'Choose image for the preview history? (y/n skip:'
2019-04-27 10:03:54 +04:00
9e05e58ac4
_
2019-04-26 21:43:43 +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
b6711b97a3
SAE added CA weights
2019-04-24 11:38:45 +04:00
947feac047
refactorings
2019-04-24 11:28:58 +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
d62785ca5a
_
2019-04-24 00:36:09 +04:00
747e39145e
_
2019-04-23 18:34:00 +04:00
ea7ec74721
change help for batch size
2019-04-23 18:31:12 +04:00
385d5dabbf
remove df-s and liae-s
2019-04-23 18:28:17 +04:00
2809d495c2
_
2019-04-23 17:31:58 +04:00
268b402513
_
2019-04-23 17:03:53 +04:00
47f9bad42b
SAE: df-s liae-s archis
2019-04-23 17:03:30 +04:00
8969e80275
_
2019-04-23 14:07:38 +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
51a917facc
back to 100* loss
2019-04-22 10:42:17 +04:00
cd2767cca0
SAE: back to batchnormalization
2019-04-22 10:28:01 +04:00
3aef9a507b
fix
2019-04-22 00:52:16 +04:00
44aa530fda
multiple preview file support for colab
2019-04-22 00:49:50 +04:00
f54cc744bd
SAE fix model crashes
2019-04-22 00:40:23 +04:00
5e3bd75007
fix
2019-04-21 22:28:25 +04:00
16053c4ae6
SAE: revert back to batchnormalization
2019-04-21 22:17:41 +04:00
093ca4dba6
fix options in ModelBase.py
2019-04-21 21:08:45 +04:00
63beb3afd2
SAE: revert back df model from prev commit. LIAE should be restarted.
2019-04-21 08:31:05 +04:00
2cdf2745a2
SAE: model will not work with this update, you should to restart training,
...
applied paper https://arxiv.org/abs/1807.01442 https://github.com/aditya-grover/uae
2019-04-20 22:33:28 +04:00
7c5f762e78
SAE:fix multiscale decoder
2019-04-20 21:30:40 +04:00
8e16f4fa1b
fix
2019-04-20 16:10:58 +04:00
3ffdc50576
nothing interesting
2019-04-20 15:22:00 +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
58d7e990f4
refactorings, added motion blur to SampleProcessor for FANSegmentator trainer
2019-04-07 23:08:00 +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
01e98cde8e
upd pixel_loss help message
2019-03-31 19:21:04 +04:00
iperov