nanodet and ncnn-webassembly-nanodet

The former project is an object detection model, while the latter is a specialized web browser deployment of that specific model using NCNN and WebAssembly, making them ecosystem siblings where one is a specific implementation/deployment of the other.

nanodet
50
Established
ncnn-webassembly-nanodet
38
Emerging
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 24/25
Maintenance 0/25
Adoption 10/25
Maturity 8/25
Community 20/25
Stars: 6,170
Forks: 1,098
Downloads: —
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 133
Forks: 27
Downloads: —
Commits (30d): 0
Language: C++
License: —
Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

About nanodet

RangiLyu/nanodet

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

Built on a FCOS-style one-stage anchor-free architecture with Generalized Focal Loss, NanoDet-Plus introduces an Assign Guidance Module (AGM) and Dynamic Soft Label Assigner (DSLA) for optimized label assignment in lightweight training, plus Ghost-PAN for efficient multi-scale feature fusion. Deployable across multiple inference frameworks—ncnn, MNN, OpenVINO—with native Android support and PyTorch training via PyTorch Lightning, achieving 34.1 mAP on COCO at competitive latency across CPU, ARM, and mobile platforms.

About ncnn-webassembly-nanodet

nihui/ncnn-webassembly-nanodet

Deploy nanodet, the super fast and lightweight object detection, in your web browser with ncnn and webassembly

Related comparisons

nanodet and ncnn-webassembly-yolov5

Scores updated daily from GitHub, PyPI, and npm data. How scores work