YOLOv5 applies the world's most advanced Artificial Intelligence (AI) to your iOS device camera scene to detect, classify and locate up to 80 classes of common objects in real-time.
YOLOv5 is trained on the COCO 2017 dataset with PyTorch and exported to Apple CoreML using our open-source GitHub repository: https://github.com/ultralytics/yolov5
A14 iOS devices perform >30 FPS at 192 x 320 default inference size. Performance may be slower on older devices.
All processing is done on-device. Images are not transmitted off-device.
For more info please visit https://github.com/ultralytics/yolov5