rkey3224@gmail.com’s Profile | Apple Developer Forums

How do I port a yolov4 or yolov5 to CoreML

I am using turicreate to train a custom object detection model, however it only supports yolov2. Has anyone tried to port v4 or v5 to CoreML . Is their a utility to do this? I have a couple of v4 PyTorch examples I was going to train then try to do this.

Posted

by

rkey3224@gmail.com.

Last updated

.

running yolov5 in swift vrs yolov2

I've started to look into the new yolov5 model, but I can't figure out the new data output format when I call it in swift. The old yolov2 model gave me result in VNRecognizedObjectObservation objects in swift code, which contained labels, confidence and coordinates for each detected object. The new model for yolov5 gives me exactly three of VNCoreMLFeatureValueObservation objects which contains none of the above. But instead contains featureName (which is some Int number) and featureValue which is a multidimensional array of some sort. And I have no idea of what to do with the new data. Does someone have any information that can help?

Core ML

Posted

by

rkey3224@gmail.com.

Last updated

.

3D IOU metrics for arkit and mlcore object detection

I am using object detection to classify an object based on a arframe passed to coreml. I know in 2d space you can calculate an IOU score, is their a way to get a IOU in arkit? It would require the x, y, z dimensions. I would like to test the IOU in three space in order to reduce the number of overlaps in already exisiting objects.

Vision

Posted

by

rkey3224@gmail.com.

Last updated

.

User Profile