---
tags:
- object-detection
library_name: coreml
license: mit
---

# YOLOv3

Locate and classify 80 different types of objects present in a camera frame or image.

## Models

- [YOLOv3](YOLOv3.mlmodel): Full precision (32 bit) model weights.
- [YOLOv3FP16](YOLOv3FP16.mlmodel): Half precision (16 bit) model weights.
- [YOLOv3Int8LUT](YOLOv3Int8LUT.mlmodel): Model optimized using 8-bit quantization with KMeans.

## Sample Code

- [Recognizing Objects in Live Capture](https://developer.apple.com/documentation/vision/recognizing_objects_in_live_capture)

## Resources

- [Original Source](https://github.com/pjreddie/darknet)
- [YOLOv3](https://arxiv.org/abs/1804.02767)