Jeffrey Gilbert

@maximeparisse face-api.js only looks for those native methods as a node server vs browser check, per my example above. There are also tfjs detections. You have to set those values...

Yes. Turned out the integrated gpu was the biggest insurmountable bottleneck to avoid blocking the rendering pipeline. I’d be willing to revisit this once tensorflow and this lib have been...

Also: https://caniuse.com/#feat=offscreencanvas

That doesn't seem right. Video.js is an HTML5 capable video player. Why would it still be using a Flash plugin which has been disabled by nearly the entire web? Flash...

Your input source should be a canvas. Whatever comes out of Video.js and the sources/formats it can pull from must be converted to canvas data ideally. Canvas has the advantages...

Recent posts on TensorFlow's blog make me think maybe there is another model that could be loaded up and used for fast results and more detailed info. https://blog.tensorflow.org/2020/11/iris-landmark-tracking-in-browser-with-MediaPipe-and-TensorFlowJS.html

Oh, also, this is happening https://www.chromestatus.com/feature/5678216012365824 And this https://blog.tensorflow.org/2020/07/tensorflow-2-meets-object-detection-api.html And most importantly, this happened https://blog.tensorflow.org/2020/04/tensorflow-lite-core-ml-delegate-faster-inference-iphones-ipads.html which will eventually manifest as this https://webmachinelearning.github.io/webnn/ and then we shouldn't have to worry about...

WebGPU is great, but that shouldn't be the only way Apple and everyone access those NPUs. My focus has been on the performance improvements using efficient non-blocking APIs. Face/object detection...

You're more versed in this than I am. My last touchpoint was 2019. That's not how I understood WebNN's approach as documented in their workflow hierarchy graphics and spec documentation,...

PS, happy you're involved and posting on these tickets! Can't make magic happen without magicians!