copilot/OpenSeeFace
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update README.md

Browse source
This commit is contained in:
Emiliana 2020-05-20 02:08:29 +02:00 • committed by GitHub
parent 0756568df1
commit 95763bfeaa
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

11
README.md
View file

@ -6,8 +6,6 @@ As Pytorch 1.3 CPU inference speed on Windows is very low, the model was convert
If anyone is curious, the name is a silly pun on the open seas and seeing faces. There's no deeper meaning.
Thanks to [@Virtual_Deat](https://twitter.com/Virtual_Deat) and [@ENiwatori](https://twitter.com/eniwatori) for helping me test things. Additional thanks to [@ArgamaWitch](https://twitter.com/ArgamaWitch) for further testing.
[Unity sample video](https://twitter.com/emiliana_vt/status/1210622149314203648) | [Sample video](https://www.youtube.com/watch?v=AOPHiAp9DBE) | [Sample video](https://www.youtube.com/watch?v=-cBSuHGdBWQ) | [Model comparison](https://www.youtube.com/watch?v=yMcJszUy7FA)
These sample videos use older versions of the tracking models. Tracking accuracy of the current models is better.
@ -173,6 +171,15 @@ Face detection is done using a custom heatmap regression based face detection mo
RetinaFace detection is based on [this](https://github.com/biubug6/Pytorch_Retinaface) implementation. The pretrained model was modified to remove unnecessary landmark detection and converted to ONNX format for a resolution of 640x640.
# Thanks!
Many thanks to everyone who helped me test things!
* [@Virtual_Deat](https://twitter.com/Virtual_Deat), who also inspired me to start working on this.
* [@ENiwatori](https://twitter.com/eniwatori) and family.
* [@ArgamaWitch](https://twitter.com/ArgamaWitch)
* [@AngelVayuu](https://twitter.com/AngelVayuu)
# License
The code and models are distributed under the BSD 2-clause license.