PoseEstimation-CoreML icon indicating copy to clipboard operation
PoseEstimation-CoreML copied to clipboard

Minimal example for image inference

Open yonatanbitton opened this issue 3 years ago • 3 comments

Hello

I am trying to use other model and it gets complicated.

I was wondering whether someone haev minimal example on how to run inference on existing image from memory? This way it will be simpler to understand how to adapt different model.

Thanks for the repo!

yonatanbitton avatar Apr 14 '21 15:04 yonatanbitton

@yonatanbitton Does the "existing image from memory" mean UIImage type on iOS? or CVPixelBuffer? Please tell me more detail about your issues.

tucan9389 avatar Apr 14 '21 19:04 tucan9389

Thanks for the response. I've managed to run your app with my model, this is very helpful, thanks! Now I want to run it on a list of png images. I am wondering how to adapt the existing code to use single image from memory. I am not sure if it should be UIImage or CVPixelBuffer. This way I am looking for some reference about how to do it.

yonatanbitton avatar Apr 14 '21 19:04 yonatanbitton

Hmm.. in this repo, there is no minimal method for inferencing just images without launching the app. When you make that kind of function, I'll appreciate it if you make PR 🙃

Here is the Q&A that looks like what you want https://developer.apple.com/forums/thread/79976

I hope it could be helpful to you.

tucan9389 avatar Apr 14 '21 19:04 tucan9389