experiencor/keras-yolo2

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).

51
/ 100
Established

This project helps you train a computer vision model to automatically detect specific objects within images or video. You provide a collection of images with your objects labeled, and the system outputs a trained model that can identify those objects in new, unseen images or video streams. This tool is ideal for researchers, analysts, or engineers who need to automate object identification for tasks like wildlife monitoring, vehicle tracking, or medical image analysis.

1,737 stars. No commits in the last 6 months.

Use this if you need to build a custom object detection system for specific items (like raccoons, kangaroos, or red blood cells) from your own image datasets.

Not ideal if you need to detect a wide variety of common objects and prefer to use a pre-trained, off-the-shelf solution without custom training.

object-detection image-analysis computer-vision-training animal-tracking medical-imaging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,737

Forks

777

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/experiencor/keras-yolo2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.