Emiliana
|
0a1bedb352
|
The face tracker now keeps track of which face is which. This makes 3D point estimation for multi face scenarios both more stable and faster.
|
2020-02-07 00:55:29 +01:00 |
|
Emiliana
|
423b5c6c86
|
The model selection parameter should now be easier to understand and two less useful models have been removed to save space. Width, height and FPS are now written to log file and both width and height are also transmitted over the network. The video output function has been changed to use a lossless codec, but videos need to be converted to a more common format before importing them to Vegas now.
|
2020-02-07 00:09:48 +01:00 |
|
Emiliana
|
18623a325f
|
These MobileNetV3 based models can be used by swapping them out for any of the two regular ShuffleNetV2 based models. They are not compatible with the smaller, faster ShuffleNetV2 model.
|
2020-02-06 23:43:49 +01:00 |
|
Emiliana
|
dda7dd0519
|
All models were retrained to fix bugs in the training process. There are also other bug fixes and improvements.
|
2020-01-26 11:47:07 +01:00 |
|
Emiliana
|
2595fa31a9
|
Information about eye blink detection
|
2020-01-03 17:08:12 +01:00 |
|
Emiliana
|
abbba992a2
|
Merge branch 'master' of github.com:emilianavt/OpenSeeFace
|
2020-01-03 16:41:07 +01:00 |
|
Emiliana
|
9f256eab75
|
Blink detection and stabilized 3D pose estimation
|
2020-01-03 16:40:45 +01:00 |
|
Emiliana
|
ca47b2e3c3
|
Information about the OpenSeeLauncher API
|
2020-01-02 14:47:51 +01:00 |
|
Emiliana
|
114ab8d44e
|
First version.
|
2020-01-02 12:24:25 +01:00 |
|