YOLOv5-Lite：Lighter, faster and easier to deploy

Perform a series of ablation experiments on yolov5 to make it lighter (smaller Flops, lower memory, and fewer parameters) and faster (add shuffle channel, yolov5 head for channel reduce. It can infer at least 10+ FPS On the Raspberry Pi 4B when input the frame with 320×320) and is easier to deploy (removing the Focus layer and four slice operations, reducing the model quantization accuracy to an acceptable range).

Comparison of ablation experiment results

See the wiki: https://github.com/ppogg/YOLOv5-Lite/wiki/Test-the-map-of-models-about-coco

Comparison on different platforms

The tutorial of 15FPS on Raspberry Pi 4B:

https://zhuanlan.zhihu.com/p/672633849

• The above is a 4-thread test benchmark
• Raspberrypi 4B enable bf16s optimization，Raspberrypi 64 Bit OS

qq交流群：993965802

入群答案:剪枝 or 蒸馏 or 量化 or 低秩分解（任意其一均可）

·Model Zoo·

@v5lite-e:

@v5lite-s:

@v5lite-c:

@v5lite-g:

Download Link：

• [ ] v5lite-e.pt: | Baidu Drive | Google Drive |
  

  |──────ncnn-fp16: | Baidu Drive | Google Drive |
  |──────ncnn-int8: | Baidu Drive | Google Drive |
  |──────mnn-e_bf16: | Google Drive |
  |──────mnn-d_bf16: | Google Drive|
  └──────onnx-fp32: | Baidu Drive | Google Drive |
  

• [ ] v5lite-s.pt: | Baidu Drive | Google Drive |
  

  |──────ncnn-fp16: | Baidu Drive | Google Drive |
  |──────ncnn-int8: | Baidu Drive | Google Drive |
  └──────tengine-fp32: | Baidu Drive | Google Drive |
  

• [ ] v5lite-c.pt: Baidu Drive | Google Drive |
  

  └──────openvino-fp16: | Baidu Drive | Google Drive |
  

• [ ] v5lite-g.pt: | Baidu Drive | Google Drive |
  

  └──────axpi-int8: Google Drive |
  

Baidu Drive Password: pogg

v5lite-s model: TFLite Float32, Float16, INT8, Dynamic range quantization, ONNX, TFJS, TensorRT, OpenVINO IR FP32/FP16, Myriad Inference Engin Blob, CoreML

https://github.com/PINTO0309/PINTO_model_zoo/tree/main/180_YOLOv5-Lite

Thanks for PINTO0309:https://github.com/PINTO0309/PINTO_model_zoo/tree/main/180_YOLOv5-Lite

How to use

Auto LabelImg

[**Link** ：https://github.com/ppogg/AutoLabelImg](https://github.com/ppogg/AutoLabelImg) You can use LabelImg based YOLOv5-5.0 and YOLOv5-Lite to AutoAnnotate, biubiubiu 🚀 🚀 🚀

Model Hub

Here, the original components of YOLOv5 and the reproduced components of YOLOv5-Lite are organized and stored in the [model hub](https://github.com/ppogg/YOLOv5-Lite/tree/master/models/hub)： 

Heatmap Analysis

```bash $ python main.py --type all ```  Updating ...

## How to deploy [**ncnn**](https://github.com/ppogg/YOLOv5-Lite/blob/master/cpp_demo/ncnn/README.md) for arm-cpu [**mnn**](https://github.com/ppogg/YOLOv5-Lite/blob/master/cpp_demo/mnn/README.md) for arm-cpu [**openvino**](https://github.com/ppogg/YOLOv5-Lite/blob/master/python_demo/openvino/README.md) x86-cpu or x86-vpu [**tensorrt(C++)**](https://github.com/ppogg/YOLOv5-Lite/blob/master/cpp_demo/tensorrt/README.md) for arm-gpu or arm-npu or x86-gpu [**tensorrt(Python)**](https://github.com/ppogg/YOLOv5-Lite/tree/master/python_demo/tensorrt) for arm-gpu or arm-npu or x86-gpu [**Android**](https://github.com/ppogg/YOLOv5-Lite/blob/master/android_demo/ncnn-android-v5lite/README.md) for arm-cpu ## Android_demo This is a Redmi phone, the processor is Snapdragon 730G, and yolov5-lite is used for detection. The performance is as follows: link: https://github.com/ppogg/YOLOv5-Lite/tree/master/android_demo/ncnn-android-v5lite Android_v5Lite-s: https://drive.google.com/file/d/1CtohY68N2B9XYuqFLiTp-Nd2kuFWgAUR/view?usp=sharing Android_v5Lite-g: https://drive.google.com/file/d/1FnvkWxxP_aZwhi000xjIuhJ_OhqOUJcj/view?usp=sharing new android app:[link] https://pan.baidu.com/s/1PRhW4fI1jq8VboPyishcIQ [keyword] pogg
## More detailed explanation #### Detailed model link: What is YOLOv5-Lite S/E model: zhihu link (Chinese): [https://zhuanlan.zhihu.com/p/400545131](https://zhuanlan.zhihu.com/p/400545131) What is YOLOv5-Lite C model: zhihu link (Chinese): [https://zhuanlan.zhihu.com/p/420737659](https://zhuanlan.zhihu.com/p/420737659) What is YOLOv5-Lite G model: zhihu link (Chinese): [https://zhuanlan.zhihu.com/p/410874403](https://zhuanlan.zhihu.com/p/410874403) How to deploy on ncnn with fp16 or int8: csdn link (Chinese): [https://blog.csdn.net/weixin_45829462/article/details/119787840](https://blog.csdn.net/weixin_45829462/article/details/119787840) How to deploy on mnn with fp16 or int8: zhihu link (Chinese): [https://zhuanlan.zhihu.com/p/672633849](https://zhuanlan.zhihu.com/p/672633849) How to deploy on onnxruntime: zhihu link (Chinese): [https://zhuanlan.zhihu.com/p/476533259](https://zhuanlan.zhihu.com/p/476533259)(old version) How to deploy on tensorrt: zhihu link (Chinese): [https://zhuanlan.zhihu.com/p/478630138](https://zhuanlan.zhihu.com/p/478630138) How to optimize on tensorrt: zhihu link (Chinese): [https://zhuanlan.zhihu.com/p/463074494](https://zhuanlan.zhihu.com/p/463074494) ## Reference https://github.com/ultralytics/yolov5 https://github.com/megvii-model/ShuffleNet-Series https://github.com/Tencent/ncnn ## Citing YOLOv5-Lite If you use YOLOv5-Lite in your research, please cite our work and give a star ⭐: ``` @misc{yolov5lite2021, title = {YOLOv5-Lite: Lighter, faster and easier to deploy}, author = {Xiangrong Chen and Ziman Gong}, doi = {10.5281/zenodo.5241425} year={2021} } ```