Anzhc/Race-Classification-FairFace-YOLOv8

Race Classification YOLOv8/11

This model is based on FairFace 0.25 padding variant dataset composed by Microsoft researchers, aiming to reduce bias by better balancing classes in dataset.

Karkkainen, Kimmo, and Joo, Jungseock.
FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 1548–1558.
FairFace Dataset on GitHub

You also can find their pretrained model here.

This YOLOv8 training is meant only for race classification. I wanted a really really fast model for tagging, and this is likely what it's useful for! I will provide a pipeline for running it on your datasets in future.

I've made simple scripts for you to use on your data. By default it will output .txt files(or append to existing), so modify for your specific needs: https://github.com/Anzhc/Simple-Utility-Scripts-for-YOLO/tree/main

Model	Target	top1_acc	Classes	Dataset size	Training Resolution
Race-CLS-FairFace_yolov8n	Face: Real	0.717	7(Black, East Asian, Indian, Latino_Hispanic, Middle Eastern, Southeast Asian, White)	~86740(train), ~10950(val)	224
Race-CLS-FairFace_yolov8s	Face: Real	0.721	7(Black, East Asian, Indian, Latino_Hispanic, Middle Eastern, Southeast Asian, White)	~86740(train), ~10950(val)	224
Race-CLS-FairFace_yolov8m	Face: Real	0.725	7(Black, East Asian, Indian, Latino_Hispanic, Middle Eastern, Southeast Asian, White)	~86740(train), ~10950(val)	224
Race-CLS-FairFace_yolo11l	Face: Real	0.733	7(Black, East Asian, Indian, Latino_Hispanic, Middle Eastern, Southeast Asian, White)	~86740(train), ~10950(val)	224
Race-CLS-FairFace_yolo11x	Face: Real	0.735	7(Black, East Asian, Indian, Latino_Hispanic, Middle Eastern, Southeast Asian, White)	~86740(train), ~10950(val)	224