Thanks for sharing! I have been working on the exact same project with Tensorflow & BodyPix, really helpful to compare notes & see the pyfakewebcam approach!
I'm iterating on it again tonight, and tentatively virtualvideo [1][2] gives better results by just piping frames into ffmpeg vs pyfakewebcam
[1]: https://github.com/Flashs/virtualvideo/ [2]: https://pypi.org/project/virtualvideo/
I'll have to update the post or do a follow-up at some point.