jveitchmichaelis/edgetpu-yolo
Minimal-dependency Yolov5 and Yolov8 export and inference demonstration for the Google Coral EdgeTPU
This project helps embedded systems developers and AI engineers deploy state-of-the-art object detection models, specifically Yolov5 and Yolov8, onto Google Coral EdgeTPU devices. It takes pre-trained object detection models and outputs highly optimized versions that can run efficiently on edge hardware. The primary users are those building intelligent vision applications for compact, low-power devices.
120 stars. No commits in the last 6 months.
Use this if you need to run fast, minimal-dependency object detection on a Google Coral EdgeTPU for applications like surveillance, robotics, or industrial automation.
Not ideal if you need to deploy complex, large-scale deep learning models that require significant computational resources or if your target hardware is not a Google Coral EdgeTPU.
Stars
120
Forks
35
Language
Python
License
—
Category
Last pushed
Apr 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jveitchmichaelis/edgetpu-yolo"
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