#367 · Primary category： Computer Vision
MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
Project last updated：02/06/21
GitHub Stars
1.7K
Forks
278
Contributors
3
License
Other
Why we included this project
This project ships compact object detectors built on MobileNetV2 backbones, with the Nano variant coming in around 3MB and under 0.5 billion FLOPs, which makes it a useful reference point for teams targeting phones or embedded devices. The repo bundles Darknet models for COCO and VOC detection plus a face-detection variant, and it shows how to convert and run them on mobile inference runtimes like NCNN and MNN, complete with benchmark tables and C sample code for a 106-point landmark detector. Anyone comparing lightweight YOLO architectures will find direct measurements across several popular tiny networks. Note that the author has since moved on to the successor Yolo-Fastest project, so treat this as a stable snapshot of proven configurations to mine for baseline numbers rather than an actively developed codebase.
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)