Hanley

Hi @oishi89 , Not entirely sure why this issue is happening to you. The multithreading should mean that the model shouldn't cause hiccups for the camera. Apple's VGG16 (553.5 MB)...

I see. That's good to know. P.S. iOS 11.1 is currently beta software, so it'll also be good to know Which Beta version you're running. You can find my email...

------------------------------------------- UPDATE: It appears LARGE MLModels are having issues in iOS 11.1 betas. Both @oishi89 's YOLO-inspired mlmodel (200mb), and Apple's VGG16 (554mb) mlmodel are having issues with iOS 11.1...

Thanks Romain! Will look into your suggestion of putting [weak self] within the mlRequest - in the future. 👍

Hi @Buthrakaur , Thank you. With the HoloKit / Aryzon / Mira Prism headsets: It is very likely you'll have to customize the eyeFOV and cameraImageScale parametres. Ideally you'd calculate...

If anyone plays with this code with any headsets (HoloKit, Aryzon, Mira Prism, etc.) - would love to hear what `eyeFOV` and `cameraImageScale` worked for you!

Same issue. Getting NaN confidences with a custom dataset. https://editor.p5js.org/hanleyweng/sketches/pRXlNix-P Update: I solved the NaN issue in my case. I suspect(ed) that my data wasn't playing well with the **normalizeData()**...