aitrack VS ncnn

Additionally you can use https://github.com/AIRLegend/aitrack to get good head tracking and you don't need to run it with the same WINE prefix, since it uses UDP to communicate. Just run it casually from your OS (via WINE for example). But OpenTrack still need to run in the same WINE prefix ofc.

Software to setup a camera with head tracking https://github.com/AIRLegend/aitrack

For rudimentary head tracking, you can use a webcam with AiTrack.

If you have a decently modern phone you can get the smoothtrack app on your phone for $10. You can use that as an input for opentrack. I've been using that for a while, and it seems to be working well. Apparently you can also use a regular webcam in opentrack using aitrack, but I haven't personally used it so I can't vouch for how well it works.

I would use ai track (https://github.com/AIRLegend/aitrack) instead of a track ir system since it only uses a decent webcam and in my experience is pretty reliable.

OpenTrack plus AITrack is 100% free. If you don't have a webcam, toss in DroidCam for Android/iOS and use your smartphone.

run opentrack https://github.com/opentrack/opentrack/releases to get the curves and mapping and aitrack https://github.com/AIRLegend/aitrack for head tracking. 200% better for me.

I use AITrack to use a webcam to read my face. This means that the only peripheral I need is a webcam, no other headsets or hats.

ncnn uses Vulkan for GPU acceleration, I've seen it used in a few projects to get AMD hardware support.

https://github.com/Tencent/ncnn

They're using NCNN to package the model. Have a look. https://github.com/Tencent/NCNN

Hi. Here is my prefered android app for realtime objet detection: https://github.com/nihui/ncnn-android-nanodet ; https://github.com/Tencent/ncnn contains a lot of android demo app for a lot of models.

ncnn home page: https://github.com/Tencent/ncnn

ncnn

Yes, Android devices tend to have bigger RAMs, making running 1024x1024 possible (this is not possible at all on iPhones, which could peak around 5GiB memory with my current implementation, some serious engineering required to bring that down on iPhone devices). The problem is I am not sure about speed. I would likely switch to NCNN (https://github.com/Tencent/ncnn) as the backend which have a decent Vulkan computing kernel support. It is definitely a possibility and there is a path to do that.

As the leading open-source inference framework in China and in the world, what we like are its almost zero cost cross-platform capability, high inference speed, and minimal deployment volume. (Project address: https://github.com/Tencent/ncnn)

If you’re not planning on training the neural net on an embedded device and just do inference, this might interest you: https://github.com/Tencent/ncnn