#204 · Primary category： Computer Vision
FastestDet
:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler
Project last updated：05/12/26
GitHub Stars
855
Forks
151
Contributors
4
License
BSD-3-Clause
Why we included this project
FastestDet is aimed at people who need object detection on hardware too weak for the usual YOLO models. The anchor-free detector packs roughly 250K parameters and has published runtimes on RK3568 and Snapdragon 835 chips, so the speed claims are measurable on real edge silicon rather than desktop GPUs. Its single-scale detection head and simpler post-processing cut down the fiddly tuning that usually comes with moving a model to a new device, and the repo includes ready-to-run test, training, and evaluation scripts for checking it on your own data. If your device is power-constrained and the bigger YOLO variants are too slow, this is a benchmarked option you can actually compare before committing to heavier weights.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)