# snnf

**Repository Path**: sunplus-group/snnf

## Basic Information

- **Project Name**: snnf
- **Description**: Sunplus提供的C++ NN Framework
- **Primary Language**: C++
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-01-21
- **Last Updated**: 2025-02-08

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README


# snnf

#### 介绍
https://sunplus.atlassian.net/wiki/spaces/C3/pages/2427224156/SP7350#SDK%E4%B8%8B%E8%BD%BD%E7%BC%96%E8%AF%91

#### 编译与部署教程
环境: SP7350 开发平台

在SP7350平台上通过下面命令下载及编译snnf代码

```
cd ~
git clone https://gitee.com/sunplus-group/snnf.git
cd snnf
cat snnf_release.part.* > snnf_release.tar.gz
rm -rf snnf_release.part.*
tar -xf snnf_release.tar.gz && tar -xf NPUSdk-6.4.18.5.tar.xz
cd snnf_release
./snnf_build.sh
```

#### 测试
编译完成后，可以通过snnf_demo/snnf_sample命令测试

1. snnf_demo测试
snnf_demo只能测试snnf内每个模型范例默认使用的模型

```
sunplus@ubuntu:~/snnf/snnf_release$ cd release

sunplus@ubuntu:~/snnf/snnf_release/release$ ./snnf_demo.sh 
Usage: ./bin/snnf_demo [-m|-s|-a|-h] [-i|-v|-o|option]
	Version: 1.2.0_V1.2.0
	Time: 2025-01-24 14:35:55 +0800
	[-m,--model <model>] run a single model
		<model>:Age                        Det10g                     HumanAttr                  
			LightFace                  OcrCls                     OcrDet                     
			OcrRec                     VehicleAttr                W600kR50                   
			YoloV8sOdMap               Yolov5sDetection           Yolov5sV1                  
			Yolov8nClassify            Yolov8sClassify            stgcn                      
			BotSortTrack               BotSortTrackStgcn          YoloV8sDetection           
			
		example:./bin/snnf_demo -m Yolov5sDetection
			./bin/snnf_demo --model HumanAttr

	[-s,--sequential <model1,model2,...>] run sequential models
		<models>:Yolov5sDetection,HumanFilter,HumanAttr
			LightFace,Age
			OcrDet,OcrRec
			OcrDet,OcrCls,OcrRec
			Det10g,W600kR50
			YoloV8sDetection,VehicleFilter,VehicleAttr
			YoloV8nDetectionOpti,BotSortTrack
			YoloV8nPoseOpti,BotSortTrackStgcn
			YoloV8nCcpdOpti,OcrRec
			YoloV8nCcpdOpti,OcrCls,OcrRec
		example:./bin/snnf_demo -s Yolov5sDetection,HumanFilter,HumanAttr
			./bin/snnf_demo --sequential OcrDet,OcrCls,OcrRec
			./bin/snnf_demo -s YoloV8nCcpdOpti,OcrRec,imageWriter
			./bin/snnf_demo -s YoloV8sDetectionOpti,BotSortTrack,videoWriter -v resource/video/humanTracking.mp4
			./bin/snnf_demo -s YoloV8nPoseOpti,BotSortTrackStgcn,videoWriter -v resource/video/person-falling.mp4

	[-i,--image file] set image file to nn detection.
		<file>: file name
		[-c | option]: test count, this parameter is only match with -i
		example:./bin/snnf_demo -s Yolov5sDetection,HumanFilter,HumanAttr -i resource/image/person.jpg -c 2
			./bin/snnf_demo -s Yolov5sDetection,HumanFilter,HumanAttr --image resource/image/person.jpg -c 2

	[-v,--video file] set video file to nn detection.
		<file>: file name
		example:./bin/snnf_demo -s YoloV8sDetectionOpti,BotSortTrack,videoWriter -v resource/video/humanTracking.mp4
			./bin/snnf_demo -s YoloV8sDetectionOpti,BotSortTrack,videoWriter --video resource/video/humanTracking.mp4

	[-o,--output file] specify the output file name for saving results.
		<file>: file name with extension (e.g., output.jpg, output.json, output.mp4)
		This parameter must be used in conjunction with imageWriter, jsonWriter, or videoWriter.
		example:./bin/snnf_demo -s Yolov5sDetection,HumanFilter,HumanAttr,imageWriter -i resource/image/person.jpg -o output.jpg
			./bin/snnf_demo -s Yolov5sDetection,HumanFilter,HumanAttr,jsonWriter -i resource/image/person.jpg -o output.json
			./bin/snnf_demo -s YoloV8sDetectionOpti,BotSortTrack,videoWriter -v resource/video/humanTracking.mp4 -o output.mp4 

	[-a,--all] run all model testing

	assist tools: imageWriter videoWriter jsonWriter BotSortTrack HumanFilter VehicleFilter
```
可以通过下面的命令测试单个模型
```
sunplus@ubuntu:~/snnf/snnf_release/release$ ./snnf_demo.sh -m Yolov5sDetection
1738997435490|7f83386040|T|common: [app]Yolov5sDetection in
1738997435889|7f5eb02b40|T|common: [app]GeneralModelOutputListener detect from resource/image/person.jpg, the result: (box: 612.44 156.84 268.88 625.51) --> label: 0(person), confidence: 0.95, fin: false
1738997435889|7f5eb02b40|T|common: [app]GeneralModelOutputListener detect from resource/image/person.jpg, the result: (box: 311.82 181.12 199.79 606.84) --> label: 0(person), confidence: 0.90, fin: false
1738997435889|7f5eb02b40|T|common: [app]GeneralModelOutputListener detect from resource/image/person.jpg, the result: (box: 448.12 283.81 76.55 186.72) --> label: 26(handbag), confidence: 0.43, fin: true
1738997435947|7f83386040|T|common: [app]Yolov5sDetection out, retVal: -0x0
```

2. snnf_sample测试

如需测试自训练模型，可以通过snnf_sample来测试，需要按照前面提供的连接文档修改模型的相关差异参数，然后在snnf_release下执行./snnf_build.sh编译代码
```
cd release
source snnf_env.sh
./bin/snnf_singleMode
```

```
sunplus@ubuntu:~/snnf/snnf_release/release$ ./bin/snnf_single_model 
1738997671944|7f88b27040|T|common: [app]the result: (box: 613.0210 151.1255 277.9775 640.6787) --> label: 0(person), confidence: 0.93, fin: false
1738997671944|7f88b27040|T|common: [app]the result: (box: 313.3374 175.0488 210.7588 617.1055) --> label: 0(person), confidence: 0.91, fin: false
1738997671944|7f88b27040|T|common: [app]the result: (box: 449.4962 286.2632 67.5105 180.4170) --> label: 26(handbag), confidence: 0.40, fin: true
```