Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
| Date | Stars |
|---|---|
| 2026-07-24 | 6238 |
| 2026-07-25 | 6238 |
| 2026-07-28 | 6238 |
| 2026-07-30 | 6238 |
| 2026-08-06 | 6238 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img src="docs/imgs/Title.jpg" /> # NanoDet-Plus **Super fast and high accuracy lightweight anchor-free object detection model. Real-time on mobile devices.** [](https://img.shields.io/github/checks-status/RangiLyu/nanodet/main?label=CI&style=flat)  [](https://github.com/RangiLyu/nanodet/blob/main/LICENSE) [](https://img.shields.io/github/downloads/RangiLyu/nanodet/total?color=yellow&label=Downloads&logo=github&logoColor=lightgrey&style=flat) [](https://img.shields.io/github/v/release/RangiLyu/nanodet?style=flat) </div> * ⚡Super lightweight: Model file is only 980KB(INT8) or 1.8MB(FP16). * ⚡Super fast: 97fps(10.23ms) on mobile ARM CPU. * 👍High accuracy: Up to **34.3 mAP<sup>val</sup>@0.5:0.95** and still realtime on CPU. * 🤗Training friendly: Much lower GPU memory cost than other models. Batch-size=80 is available on GTX1060 6G. * 😎Easy to deploy: Support various backends including **ncnn, MNN and OpenVINO**. Also provide **Android demo** based on ncnn inference framework. **** # Introduction  NanoDet is a FCOS-style one-stage anchor-free object detection model which using [Generalized Focal Loss](https://arxiv.org/pdf/2006.04388.pdf) as classification and regression loss. In NanoDet-Plus, we propose a novel label assignment strategy with a simple **assign guidance module (AGM)** and a **dynamic soft label assigner (DSLA)** to solve the optimal label assignment problem in lightweight model training. We also introduce a light feature pyramid called Ghost-PAN to enhance multi-layer feature fusion. These improvements boost previous NanoDet's detection accuracy by **7 mAP** on COCO dataset. [NanoDet-Plus 知乎中文介绍](https://zhuanlan.zhihu.com/p/449912627) [NanoDet 知乎中文介绍](https://zhuanlan.zhihu.com/p/306530300) QQ交流群：908606542 (答案：炼丹) **** ## Benchmarks Model |Resolution| mAP<sup>val<br>0.5:0.95 |CPU Latency<sup><br>(i7-8700) |ARM Latency<sup><br>(4xA76) | FLOPS | Params | Model Size :-------------:|:--------:|:-------:|:--------------------:|:--------------------:|:----------:|:---------:|:-------: NanoDet-m | 320*320 | 20.6 | **4.98ms** | **10.23ms** | **0.72G** | **0.95M** | **1.8MB(FP16)** | **980KB(INT8)** **NanoDet-Plus-m** | 320*320 | **27.0** | **5.25ms** | **11.97ms** | **0.9G** | **1.17M** | **2.3MB(FP16)** | **1.2MB(INT8)** **NanoDet-Plus-m** | 416*416 | **30.4** | **8.32ms** | **19.77ms** | **1.52G** | **1.17M** | **2.3MB(FP16)** | **1.2MB(INT8)** **NanoDet-Plus-m-1.5x** | 320*320 | **29.9** | **7.21ms** | **15.90ms** | **1.75G** | **2.44M** | **4.7MB(FP16)** | **2.3MB(INT8)** **NanoDet-Plus-m-1.5x** | 416*416 | **34.1** | **11.50ms** | **25.49ms** | **2.97G** | **2.44M** | **4.7MB(FP16)** | **2.3MB(INT8)** YOLOv3-Tiny | 416*416 | 16.6 | - | 37.6ms | 5.62G | 8.86M | 33.7MB YOLOv4-Tiny | 416*416 | 21.7 | - | 32.81ms | 6.96G | 6.06M | 23.0MB YOLOX-Nano | 416*416 | 25.8 | - | 23.08ms | 1.08G | 0.91M | 1.8MB(FP16) YOLOv5-n | 640*640 | 28.4 | - | 44.39ms | 4.5G | 1.9M | 3.8MB(FP16) FBNetV5 | 320*640 | 30.4 | - | - | 1.8G | - | - Mobil
Excerpt of 14,690 characters
Read on GitHub
Shanghai AI Laboratory · China
317
8
weida wang
5
China
4
2
SongHe · Shenzhen University
2
Florian Bruggisser · @bildspur · Switzerland
2
Cai Shanli
2
1
1
1
1
Alex Dadukin · United Kingdom
1
Zhiqiang Wang · axera · China
1
Yaojie Shen · ByteDance Inc. · China
1
Zhuo Zhang · China
1
China
1
1
1
Pei-Lin Wu · Wuxi Biologics
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:34e364259a444a23, topic:deep-learning, topic:pytorch
matched fp:34e364259a444a23, topic:object-detection, desc:object detection, readme:object detection