Spinkoo/Embedded-Yolov7

Compress, Deploy and Inference YOLOv7 on low-cost MCUs

27
/ 100
Experimental

This framework helps embedded systems engineers take a trained YOLOv7 object detection model and prepare it for deployment on low-cost, low-power microcontrollers like STM32 chips. It takes a trained YOLOv7 model, compresses it significantly, and then generates the necessary code to run object detection directly on resource-constrained devices. It's for embedded engineers who need to add real-time object detection capabilities to hardware with limited memory and processing power.

Use this if you are an embedded systems engineer developing products that require on-device object detection using YOLOv7 on microcontrollers, minimizing hardware costs and power consumption.

Not ideal if you are developing on high-performance platforms like GPUs or need to deploy non-YOLO object detection models.

embedded-systems edge-ai object-detection microcontroller-programming firmware-development
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

GPL-3.0

Last pushed

Oct 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Spinkoo/Embedded-Yolov7"

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