trysem/YOLOv8_head_detector
By trysem · ↓ 0 · ♥ 0 · Updated 2026-03-17
What's in this repo
This page lists the files in trysem/YOLOv8_head_detector, including yolo-head-medium.onnx, yolo-head-nano.onnx.
- 2 ONNX models (.onnx files)
- 4 files, including 2 .onnx, 1 .md
- Last updated 2026-03-17
ONNX files
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
ONNX version of https://github.com/Abcfsa/YOLOv8_head_detector
YOLOv8_head_detector model trained for head detection,graduation project 2023-24
Info These model are trained with yolov8 on the dataset SCUT-HEAD part A and part B. medium.pt is bigger and more accurate while nano.pt is smaller and faster.
Usage If you already have ultralytics/yolov8 installed,then just choose one of these two models to do your prediction jobs. Else first enter these in the command line
pip install ultralytics pip install opencv-python pip install pandas Basic usage:
python example.py --model path/to/model_weights.pt --source path/to/img_folder --output path/to/save.csv --mode track/detect Output format Depends on mode.If mode is detect,then the columns would be ["name","xmin","ymin","xmax","ymax"]. If mode is track,then there will be an additional "id" column between "name" and "xmin". Output has no index column "xmin",...,"ymax" are all normalized to 0-1.
Model info
Created: 2026-03-17
Updated: 2026-03-17
View on Hugging Face