dog-qiuqiu / Yolo-Fastest
Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
☆2,043Updated 3 years ago
Alternatives and similar repositories for Yolo-Fastest:
Users that are interested in Yolo-Fastest are comparing it to the libraries listed below
- Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smar…☆846Updated last year
- NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone…☆5,898Updated 7 months ago
- 🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署,支持Android与iOS。☆1,526Updated 2 years ago
- PyTorch implementation of YOLOv4