RangiLyu/nanodet
NanoDet-Plusā”Super fast and lightweight anchor-free object detection model. š„Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphoneš„
This project helps integrate real-time object detection capabilities into mobile applications or edge devices. It takes camera feeds or images as input and identifies objects within them, providing their location and classification. This is ideal for mobile developers or engineers building applications that need to quickly understand what's in a scene, such as for smart devices or automated systems.
6,170 stars. No commits in the last 6 months.
Use this if you need extremely fast and lightweight object detection that can run directly on mobile phone processors or other resource-constrained hardware with high accuracy.
Not ideal if your application requires detecting extremely small or obscure objects with maximum precision, or if you have ample computational resources and prioritize absolute best-in-class accuracy over speed and size.
Stars
6,170
Forks
1,098
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/RangiLyu/nanodet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
PINTO0309/OpenVINO-YoloV3
YoloV3/tiny-YoloV3+RaspberryPi3/Ubuntu LaptopPC+NCS/NCS2+USB Camera+Python+OpenVINO
dog-qiuqiu/MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops...
Qengineering/Face-Recognition-Jetson-Nano
Recognize 2000+ faces on your Jetson Nano with database auto-fill and anti-spoofing
Qengineering/YoloV8-NPU
YoloV8 NPU for the RK3566/68/88
Qengineering/Face-Recognition-Raspberry-Pi-64-bits
Recognize 2000+ faces on your Raspberry Pi 4 with database auto-fill and anti-spoofing