PINTO0309/crowdhuman_hollywoodhead_yolo_convert
YOLOv7 training. Generates a head-only dataset in YOLO format. The labels included in the CrowdHuman dataset are Head and FullBody, but ignore FullBody.
This tool helps computer vision engineers prepare image datasets for training 'head detection' models. It takes raw CrowdHuman and HollywoodHeads datasets, extracts only the head annotations, and converts them into the YOLO format. The output is a highly curated dataset ready for direct use in YOLOv7 model training.
No commits in the last 6 months.
Use this if you need to train a computer vision model specifically to detect human heads in images using YOLOv7, and you want to leverage existing large datasets efficiently.
Not ideal if you need to detect full bodies, other objects, or are using a different object detection framework than YOLOv7.
Stars
32
Forks
2
Language
Python
License
GPL-3.0
Category
Last pushed
Jun 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PINTO0309/crowdhuman_hollywoodhead_yolo_convert"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
saimj7/People-Counting-in-Real-Time
People Counting in Real-Time with an IP camera.
Hironsan/BossSensor
Hide screen when boss is approaching.
brian-yu/pedestrian-cam
Monitoring Foot Traffic over IP Webcams with ML
lunarwhite/yolo-student-counter
Monitor in classroom headcount, support image/video/live streaming as input. 教室人数检测统计
intel-iot-devkit/people-counter-python
Create a smart video application using the Intel Distribution of OpenVINO toolkit. The toolkit...