Commit graph

15 commits

Author SHA1 Message Date
Colombo
dd1d5e8909 improved face align,
More stable and precise version of the face transformation matrix.
Now full_faces are aligned with the upper and lateral boundaries of the frame,
result: fix of cutted mouth, increase area of the cheeks of side faces
before/after https://i.imgur.com/t9IyGZv.jpg
therefore, additional training is required for existing models.
Optionally, you can re-extract dst faces of your project, if they have problems with cutted mouth or cheeks.
2019-12-19 18:33:04 +04:00
Colombo
e8673e3fcc nothing interesting 2019-12-11 22:33:23 +04:00
Colombo
77b390c04b 1 2019-11-24 19:51:07 +04:00
Colombo
b9c0815d17 added random shuffle to samples in SampleGeneratorFace.py 2019-11-11 11:35:46 +04:00
Colombo
b9c41a269d fix check no training data provided 2019-10-25 00:27:34 +04:00
Colombo
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
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
8d7edd172c random_ct_sample - now not applying with 20% chance 2019-05-11 19:40:02 +04:00
iperov
a805f81142 SAE: added test option: 'Apply random color transfer to src faceset' 2019-05-06 11:34:56 +04:00
iperov
c0a63addd4 SampleGeneratorFace optimizations 2019-04-24 21:27:05 +04:00
iperov
8969e80275 _ 2019-04-23 14:07:38 +04:00
iperov
e58197ca22 initial code to extract umdfaces.io dataset and train pose estimator 2019-04-23 08:14:09 +04:00
iperov
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
iperov
3cf3bb786e rename samples to samplelib 2019-03-27 10:44:13 +04:00
Renamed from samples/SampleGeneratorFace.py (Browse further)