Spinkoo/Embedded-Yolov7
Compress, Deploy and Inference YOLOv7 on low-cost MCUs
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.
Stars
14
Forks
—
Language
Python
License
GPL-3.0
Category
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.
Higher-rated alternatives
ultralytics/yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
ultralytics/yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
mindspore-lab/mindyolo
A toolbox of yolo models and algorithms based on MindSpore
ultralytics/assets
Ultralytics assets
stephanecharette/DarkHelp
C++ wrapper library for Darknet