🛠Lite.Ai.ToolKit: A lite C++ toolkit of awesome AI models, such as Object Detection, Face Detection, Face Recognition, Segmentation, Matting, etc. See Model Zoo and ONNX Hub, MNN Hub, TNN Hub, NCNN Hub. (❤️ Star 🌟👆🏻 this repo to support me if it does any helps to you, thanks ~)

English | 中文文档 | MacOS | Linux | Windows

Features 👏👋

• Simply and User friendly. Simply and Consistent syntax like lite::cv::Type::Class, see examples.
• Minimum Dependencies. Only OpenCV and ONNXRuntime are required by default, see build.
• Lots of Algorithm Modules. Contains almost 300+ C++ re-implementations and 500+ weights.

Tools

Training	Visualizing	Better Performance	About LLM Inference 🔥
torchlm	netron-vscode-extension	⚡️FastDeploy	Awesome-LLM-Inference

• torchlm: A high level Training and Evaluating Toolkit for Face Landmarks Detection is available at torchlm.
• netron-vscode-extension: A vscode extension for netron is avaliable at netron-vscode-extension, support *.pdmodel, *.nb, *.onnx, *.pb, *.h5, *.tflite, *.pth, *.pt, *.mnn, *.param, etc.
• FastDeploy: For better deployment experience, please try PaddlePaddle/FastDeploy. ⚡️FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with 📦out-of-the-box and unified experience, 🔚end-to-end optimization for over 🔥160+ Text, Vision, Speech and Cross-modal AI models. Support C, C++, Java, Python, CSharp etc.
• Awesome-LLM-Inference: A small Collection for Awesome LLM inference papers with codes, contains LLM.int8(), streaming-llm, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention 1/2, PagedAttention etc.

Citations 🎉🎉

Consider to cite it as follows if you use Lite.Ai.ToolKit in your projects.

@misc{lite.ai.toolkit2021,
  title={lite.ai.toolkit: A lite C++ toolkit of awesome AI models.},
  url={https://github.com/DefTruth/lite.ai.toolkit},
  note={Open-source software available at https://github.com/DefTruth/lite.ai.toolkit},
  author={Yan Jun},
  year={2021}
}

Downloads & RoadMap ✅

Some prebuilt lite.ai.toolkit libs for MacOS(x64) and Linux(x64) are available, you can download the libs from the release links. Further, prebuilt libs for Windows(x64) and Android will be coming soon ~ Please, see issues#48 for more details of the prebuilt plan and refer to releases for more available prebuilt libs.

• lite0.1.1-osx10.15.x-ocv4.5.2-ffmpeg4.2.2-onnxruntime1.8.1.zip
• lite0.1.1-osx10.15.x-ocv4.5.2-ffmpeg4.2.2-onnxruntime1.9.0.zip
• lite0.1.1-osx10.15.x-ocv4.5.2-ffmpeg4.2.2-onnxruntime1.10.0.zip
• lite0.1.1-ubuntu18.04-ocv4.5.2-ffmpeg4.2.2-onnxruntime1.8.1.zip
• lite0.1.1-ubuntu18.04-ocv4.5.2-ffmpeg4.2.2-onnxruntime1.9.0.zip
• lite0.1.1-ubuntu18.04-ocv4.5.2-ffmpeg4.2.2-onnxruntime1.10.0.zip

In Linux, in order to link the prebuilt libs, you need to export lite.ai.toolkit/lib to LD_LIBRARY_PATH first.

export LD_LIBRARY_PATH=YOUR-PATH-TO/lite.ai.toolkit/lib:$LD_LIBRARY_PATH
export LIBRARY_PATH=YOUR-PATH-TO/lite.ai.toolkit/lib:$LIBRARY_PATH  # (may need)

Quick Setup 👀

To quickly setup lite.ai.toolkit, you can follow the CMakeLists.txt listed as belows. 👇👀

set(LITE_AI_DIR ${CMAKE_SOURCE_DIR}/lite.ai.toolkit)
include_directories(${LITE_AI_DIR}/include)
link_directories(${LITE_AI_DIR}/lib})
set(TOOLKIT_LIBS lite.ai.toolkit onnxruntime)
set(OpenCV_LIBS opencv_core opencv_imgcodecs opencv_imgproc opencv_video opencv_videoio)

add_executable(lite_yolov5 examples/test_lite_yolov5.cpp)
target_link_libraries(lite_yolov5 ${TOOLKIT_LIBS} ${OpenCV_LIBS})

Contents 📖💡

• Core Features
• Quick Start
• RoadMap
• Important Updates
• Supported Models Matrix
• Build Docs
• Model Zoo
• Examples
• License
• References
• Contribute

1. Quick Start 🌟🌟

Example0: Object Detection using YOLOv5. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/yolov5s.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_yolov5_1.jpg";
  std::string save_img_path = "../../../logs/test_lite_yolov5_1.jpg";

  auto *yolov5 = new lite::cv::detection::YoloV5(onnx_path); 
  std::vector<lite::types::Boxf> detected_boxes;
  cv::Mat img_bgr = cv::imread(test_img_path);
  yolov5->detect(img_bgr, detected_boxes);
  
  lite::utils::draw_boxes_inplace(img_bgr, detected_boxes);
  cv::imwrite(save_img_path, img_bgr);  
  
  delete yolov5;
}

2. Important Updates 🆕

Click here to see details of Important Updates!

Date	Model	C++	Paper	Code	Awesome	Type
【2022/04/03】	MODNet	link	AAAI 2022	code		matting
【2022/03/23】	PIPNtet	link	CVPR 2021	code		face::align
【2022/01/19】	YOLO5Face	link	arXiv 2021	code		face::detect
【2022/01/07】	SCRFD	link	CVPR 2021	code		face::detect
【2021/12/27】	NanoDetPlus	link	blog	code		detection
【2021/12/08】	MGMatting	link	CVPR 2021	code		matting
【2021/11/11】	YoloV5_V_6_0	link	doi	code		detection
【2021/10/26】	YoloX_V_0_1_1	link	arXiv 2021	code		detection
【2021/10/02】	NanoDet	link	blog	code		detection
【2021/09/20】	RobustVideoMatting	link	WACV 2022	code		matting
【2021/09/02】	YOLOP	link	arXiv 2021	code		detection

3. Supported Models Matrix

• / = not supported now.
• ✅ = known work and official supported now.
• ✔️ = known work, but unofficial supported now.
• ❔ = in my plan, but not coming soon, maybe a few months later.

Class	Size	Type	Demo	ONNXRuntime	MNN	NCNN	TNN	MacOS	Linux	Windows	Android
YoloV5	28M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
YoloV3	236M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
TinyYoloV3	33M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
YoloV4	176M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
SSD	76M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
SSDMobileNetV1	27M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
YoloX	3.5M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
TinyYoloV4VOC	22M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
TinyYoloV4COCO	22M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
YoloR	39M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
ScaledYoloV4	270M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
EfficientDet	15M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
EfficientDetD7	220M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
EfficientDetD8	322M	detection	demo	✅	/	/	/	✅	✔️	✔️	/
YOLOP	30M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
NanoDet	1.1M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
NanoDetPlus	4.5M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
NanoDetEffi...	12M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
YoloX_V_0_1_1	3.5M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
YoloV5_V_6_0	7.5M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
GlintArcFace	92M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
GlintCosFace	92M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
GlintPartialFC	170M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
FaceNet	89M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
FocalArcFace	166M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
FocalAsiaArcFace	166M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
TencentCurricularFace	249M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
TencentCifpFace	130M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
CenterLossFace	280M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
SphereFace	80M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
PoseRobustFace	92M	faceid	demo	✅	/	/	/	✅	✔️	✔️	/
NaivePoseRobustFace	43M	faceid	demo	✅	/	/	/	✅	✔️	✔️	/
MobileFaceNet	3.8M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
CavaGhostArcFace	15M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
CavaCombinedFace	250M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	/
MobileSEFocalFace	4.5M	faceid	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
RobustVideoMatting	14M	matting	demo	✅	✅	/	✅	✅	✔️	✔️	❔
MGMatting	113M	matting	demo	✅	✅	/	✅	✅	✔️	✔️	/
MODNet	24M	matting	demo	✅	✅	✅	✅	✅	✔️	✔️	/
MODNetDyn	24M	matting	demo	✅	/	/	/	✅	✔️	✔️	/
BackgroundMattingV2	20M	matting	demo	✅	✅	/	✅	✅	✔️	✔️	/
BackgroundMattingV2Dyn	20M	matting	demo	✅	/	/	/	✅	✔️	✔️	/
UltraFace	1.1M	face::detect	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
RetinaFace	1.6M	face::detect	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
FaceBoxes	3.8M	face::detect	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
FaceBoxesV2	3.8M	face::detect	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
SCRFD	2.5M	face::detect	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
YOLO5Face	4.8M	face::detect	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
PFLD	1.0M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
PFLD98	4.8M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
MobileNetV268	9.4M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
MobileNetV2SE68	11M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
PFLD68	2.8M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
FaceLandmark1000	2.0M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
PIPNet98	44.0M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
PIPNet68	44.0M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
PIPNet29	44.0M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
PIPNet19	44.0M	face::align	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
FSANet	1.2M	face::pose	demo	✅	✅	/	✅	✅	✔️	✔️	❔
AgeGoogleNet	23M	face::attr	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
GenderGoogleNet	23M	face::attr	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
EmotionFerPlus	33M	face::attr	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
VGG16Age	514M	face::attr	demo	✅	✅	✅	✅	✅	✔️	✔️	/
VGG16Gender	512M	face::attr	demo	✅	✅	✅	✅	✅	✔️	✔️	/
SSRNet	190K	face::attr	demo	✅	✅	/	✅	✅	✔️	✔️	❔
EfficientEmotion7	15M	face::attr	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
EfficientEmotion8	15M	face::attr	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
MobileEmotion7	13M	face::attr	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
ReXNetEmotion7	30M	face::attr	demo	✅	✅	/	✅	✅	✔️	✔️	/
EfficientNetLite4	49M	classification	demo	✅	✅	/	✅	✅	✔️	✔️	/
ShuffleNetV2	8.7M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
DenseNet121	30.7M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	/
GhostNet	20M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
HdrDNet	13M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
IBNNet	97M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	/
MobileNetV2	13M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
ResNet	44M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	/
ResNeXt	95M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	/
DeepLabV3ResNet101	232M	segmentation	demo	✅	✅	✅	✅	✅	✔️	✔️	/
FCNResNet101	207M	segmentation	demo	✅	✅	✅	✅	✅	✔️	✔️	/
FastStyleTransfer	6.4M	style	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
Colorizer	123M	colorization	demo	✅	✅	/	✅	✅	✔️	✔️	/
SubPixelCNN	234K	resolution	demo	✅	✅	/	✅	✅	✔️	✔️	❔
SubPixelCNN	234K	resolution	demo	✅	✅	/	✅	✅	✔️	✔️	❔
InsectDet	27M	detection	demo	✅	✅	/	✅	✅	✔️	✔️	❔
InsectID	22M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	✔️
PlantID	30M	classification	demo	✅	✅	✅	✅	✅	✔️	✔️	✔️
YOLOv5BlazeFace	3.4M	face::detect	demo	✅	✅	/	/	✅	✔️	✔️	❔
YoloV5_V_6_1	7.5M	detection	demo	✅	✅	/	/	✅	✔️	✔️	❔
HeadSeg	31M	segmentation	demo	✅	✅	/	✅	✅	✔️	✔️	❔
FemalePhoto2Cartoon	15M	style	demo	✅	✅	/	✅	✅	✔️	✔️	❔
FastPortraitSeg	400k	segmentation	demo	✅	✅	/	/	✅	✔️	✔️	❔
PortraitSegSINet	380k	segmentation	demo	✅	✅	/	/	✅	✔️	✔️	❔
PortraitSegExtremeC3Net	180k	segmentation	demo	✅	✅	/	/	✅	✔️	✔️	❔
FaceHairSeg	18M	segmentation	demo	✅	✅	/	/	✅	✔️	✔️	❔
HairSeg	18M	segmentation	demo	✅	✅	/	/	✅	✔️	✔️	❔
MobileHumanMatting	3M	matting	demo	✅	✅	/	/	✅	✔️	✔️	❔
MobileHairSeg	14M	segmentation	demo	✅	✅	/	/	✅	✔️	✔️	❔
YOLOv6	17M	detection	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
FaceParsingBiSeNet	50M	segmentation	demo	✅	✅	✅	✅	✅	✔️	✔️	❔
FaceParsingBiSeNetDyn	50M	segmentation	demo	✅	/	/	/	/	✔️	✔️	❔

4. Build Docs.

• MacOS: Build the shared lib of Lite.Ai.ToolKit for MacOS from sources. Note that Lite.Ai.ToolKit uses onnxruntime as default backend, for the reason that onnxruntime supports the most of onnx's operators.

    git clone --depth=1 https://github.com/DefTruth/lite.ai.toolkit.git  # latest
    cd lite.ai.toolkit && sh ./build.sh  # On MacOS, you can use the built OpenCV, ONNXRuntime, MNN, NCNN and TNN libs in this repo.

💡 Linux and Windows.

Linux and Windows.

⚠️ Lite.Ai.ToolKit is not directly support Linux and Windows now. For Linux and Windows, you need to build or download(if have official builts) the shared libs of OpenCV、ONNXRuntime and any other Engines(like MNN, NCNN, TNN) firstly, then put the headers into the specific directories or just let these directories unchange(use the headers offer by this repo, the header file of the dependent library of this project is directly copied from the corresponding official library). However, the dynamic libraries under different operating systems need to be recompiled or downloaded. MacOS users can directly use the dynamic libraries of each dependent library provided by this project:

• lite.ai.toolkit/opencv2

    cp -r you-path-to-downloaded-or-built-opencv/include/opencv4/opencv2 lite.ai.toolkit/opencv2

• lite.ai.toolkit/onnxruntime

    cp -r you-path-to-downloaded-or-built-onnxruntime/include/onnxruntime lite.ai.toolkit/onnxruntime

• lite.ai.toolkit/MNN

    cp -r you-path-to-downloaded-or-built-MNN/include/MNN lite.ai.toolkit/MNN

• lite.ai.toolkit/ncnn

    cp -r you-path-to-downloaded-or-built-ncnn/include/ncnn lite.ai.toolkit/ncnn

• lite.ai.toolkit/tnn

    cp -r you-path-to-downloaded-or-built-TNN/include/tnn lite.ai.toolkit/tnn

and put the libs into lite.ai.toolkit/lib/(linux|windows) directory. Please reference the build-docs¹ for third_party.

• lite.ai.toolkit/lib/(linux|windows)

    cp you-path-to-downloaded-or-built-opencv/lib/*opencv* lite.ai.toolkit/lib/(linux|windows)/
    cp you-path-to-downloaded-or-built-onnxruntime/lib/*onnxruntime* lite.ai.toolkit/lib/(linux|windows)/
    cp you-path-to-downloaded-or-built-MNN/lib/*MNN* lite.ai.toolkit/lib/(linux|windows)/
    cp you-path-to-downloaded-or-built-ncnn/lib/*ncnn* lite.ai.toolkit/lib/(linux|windows)/
    cp you-path-to-downloaded-or-built-TNN/lib/*TNN* lite.ai.toolkit/lib/(linux|windows)/

Note, your also need to install ffmpeg(<=4.2.2) in Linux to support the opencv videoio module. See issue#203. In MacOS, ffmpeg4.2.2 was been package into lite.ai.toolkit, thus, no installation need in OSX. In Windows, ffmpeg was been package into opencv dll prebuilt by the team of opencv. Please make sure -DWITH_FFMPEG=ON and check the configuration info when building opencv.

• first, build ffmpeg(<=4.2.2) from source.

git clone --depth=1 https://git.ffmpeg.org/ffmpeg.git -b n4.2.2
cd ffmpeg
./configure --enable-shared --disable-x86asm --prefix=/usr/local/opt/ffmpeg --disable-static
make -j8
make install

• then, build opencv with -DWITH_FFMPEG=ON, just like

#!/bin/bash

mkdir build
cd build

cmake .. \
  -D CMAKE_BUILD_TYPE=Release \
  -D CMAKE_INSTALL_PREFIX=your-path-to-custom-dir \
  -D BUILD_TESTS=OFF \
  -D BUILD_PERF_TESTS=OFF \
  -D BUILD_opencv_python3=OFF \
  -D BUILD_opencv_python2=OFF \
  -D BUILD_SHARED_LIBS=ON \
  -D BUILD_opencv_apps=OFF \
  -D WITH_FFMPEG=ON 
  
make -j8
make install
cd ..

after built opencv, you can follow the steps to build lite.ai.toolkit.

• Windows: You can reference to issue#6

• Linux: The Docs and Docker image for Linux will be coming soon ~ issue#2

• Happy News !!! : 🚀 You can download the latest ONNXRuntime official built libs of Windows, Linux, MacOS and Arm !!! Both CPU and GPU versions are available. No more attentions needed pay to build it from source. Download the official built libs from v1.8.1. I have used version 1.7.0 for Lite.Ai.ToolKit now, you can download it from v1.7.0, but version 1.8.1 should also work, I guess ~ 🙃🤪🍀. For OpenCV, try to build from source(Linux) or down load the official built(Windows) from OpenCV 4.5.3. Then put the includes and libs into specific directory of Lite.Ai.ToolKit.

• GPU Compatibility for Windows: See issue#10.

• GPU Compatibility for Linux: See issue#97.

🔑️ How to link Lite.Ai.ToolKit?

* To link Lite.Ai.ToolKit, you can follow the CMakeLists.txt listed belows.

cmake_minimum_required(VERSION 3.10)
project(lite.ai.toolkit.demo)

set(CMAKE_CXX_STANDARD 11)

# setting up lite.ai.toolkit
set(LITE_AI_DIR ${CMAKE_SOURCE_DIR}/lite.ai.toolkit)
set(LITE_AI_INCLUDE_DIR ${LITE_AI_DIR}/include)
set(LITE_AI_LIBRARY_DIR ${LITE_AI_DIR}/lib)
include_directories(${LITE_AI_INCLUDE_DIR})
link_directories(${LITE_AI_LIBRARY_DIR})

set(OpenCV_LIBS
        opencv_highgui
        opencv_core
        opencv_imgcodecs
        opencv_imgproc
        opencv_video
        opencv_videoio
        )
# add your executable
set(EXECUTABLE_OUTPUT_PATH ${CMAKE_SOURCE_DIR}/examples/build)

add_executable(lite_rvm examples/test_lite_rvm.cpp)
target_link_libraries(lite_rvm
        lite.ai.toolkit
        onnxruntime
        MNN  # need, if built lite.ai.toolkit with ENABLE_MNN=ON,  default OFF
        ncnn # need, if built lite.ai.toolkit with ENABLE_NCNN=ON, default OFF 
        TNN  # need, if built lite.ai.toolkit with ENABLE_TNN=ON,  default OFF 
        ${OpenCV_LIBS})  # link lite.ai.toolkit & other libs.

cd ./build/lite.ai.toolkit/lib && otool -L liblite.ai.toolkit.0.0.1.dylib 
liblite.ai.toolkit.0.0.1.dylib:
        @rpath/liblite.ai.toolkit.0.0.1.dylib (compatibility version 0.0.1, current version 0.0.1)
        @rpath/libopencv_highgui.4.5.dylib (compatibility version 4.5.0, current version 4.5.2)
        @rpath/libonnxruntime.1.7.0.dylib (compatibility version 0.0.0, current version 1.7.0)
        ...

cd ../ && tree .
├── bin
├── include
│   ├── lite
│   │   ├── backend.h
│   │   ├── config.h
│   │   └── lite.h
│   └── ort
└── lib
    └── liblite.ai.toolkit.0.0.1.dylib

• Run the built examples:

cd ./build/lite.ai.toolkit/bin && ls -lh | grep lite
-rwxr-xr-x  1 root  staff   301K Jun 26 23:10 liblite.ai.toolkit.0.0.1.dylib
...
-rwxr-xr-x  1 root  staff   196K Jun 26 23:10 lite_yolov4
-rwxr-xr-x  1 root  staff   196K Jun 26 23:10 lite_yolov5
...

./lite_yolov5
LITEORT_DEBUG LogId: ../../../hub/onnx/cv/yolov5s.onnx
=============== Input-Dims ==============
...
detected num_anchors: 25200
generate_bboxes num: 66
Default Version Detected Boxes Num: 5

To link lite.ai.toolkit shared lib. You need to make sure that OpenCV and onnxruntime are linked correctly. A minimum example to show you how to link the shared lib of Lite.AI.ToolKit correctly for your own project can be found at CMakeLists.txt.

5. Model Zoo.

Lite.Ai.ToolKit contains almost 100+ AI models with 500+ frozen pretrained files now. Most of the files are converted by myself. You can use it through lite::cv::Type::Class syntax, such as lite::cv::detection::YoloV5. More details can be found at Examples for Lite.Ai.ToolKit. Note, for Google Drive, I can not upload all the *.onnx files because of the storage limitation (15G).

File	Baidu Drive	Google Drive	Docker Hub	Hub (Docs)
ONNX	Baidu Drive code: 8gin	Google Drive	ONNX Docker v0.1.22.01.08 (28G), v0.1.22.02.02 (400M)	ONNX Hub
MNN	Baidu Drive code: 9v63	❔	MNN Docker v0.1.22.01.08 (11G), v0.1.22.02.02 (213M)	MNN Hub
NCNN	Baidu Drive code: sc7f	❔	NCNN Docker v0.1.22.01.08 (9G), v0.1.22.02.02 (197M)	NCNN Hub
TNN	Baidu Drive code: 6o6k	❔	TNN Docker v0.1.22.01.08 (11G), v0.1.22.02.02 (217M)	TNN Hub

  docker pull qyjdefdocker/lite.ai.toolkit-onnx-hub:v0.1.22.01.08  # (28G)
  docker pull qyjdefdocker/lite.ai.toolkit-mnn-hub:v0.1.22.01.08   # (11G)
  docker pull qyjdefdocker/lite.ai.toolkit-ncnn-hub:v0.1.22.01.08  # (9G)
  docker pull qyjdefdocker/lite.ai.toolkit-tnn-hub:v0.1.22.01.08   # (11G)
  docker pull qyjdefdocker/lite.ai.toolkit-onnx-hub:v0.1.22.02.02  # (400M) + YOLO5Face
  docker pull qyjdefdocker/lite.ai.toolkit-mnn-hub:v0.1.22.02.02   # (213M) + YOLO5Face
  docker pull qyjdefdocker/lite.ai.toolkit-ncnn-hub:v0.1.22.02.02  # (197M) + YOLO5Face
  docker pull qyjdefdocker/lite.ai.toolkit-tnn-hub:v0.1.22.02.02   # (217M) + YOLO5Face

❇️ Lite.Ai.ToolKit modules.

Namespace and Lite.Ai.ToolKit modules.

Namespace	Details
lite::cv::detection	Object Detection. one-stage and anchor-free detectors, YoloV5, YoloV4, SSD, etc. ✅
lite::cv::classification	Image Classification. DensNet, ShuffleNet, ResNet, IBNNet, GhostNet, etc. ✅
lite::cv::faceid	Face Recognition. ArcFace, CosFace, CurricularFace, etc. ❇️
lite::cv::face	Face Analysis. detect, align, pose, attr, etc. ❇️
lite::cv::face::detect	Face Detection. UltraFace, RetinaFace, FaceBoxes, PyramidBox, etc. ❇️
lite::cv::face::align	Face Alignment. PFLD(106), FaceLandmark1000(1000 landmarks), PRNet, etc. ❇️
lite::cv::face::align3d	3D Face Alignment. FaceMesh(468 3D landmarks), IrisLandmark(71+5 3D landmarks), etc. ❇️
lite::cv::face::pose	Head Pose Estimation. FSANet, etc. ❇️
lite::cv::face::attr	Face Attributes. Emotion, Age, Gender. EmotionFerPlus, VGG16Age, etc. ❇️
lite::cv::segmentation	Object Segmentation. Such as FCN, DeepLabV3, etc. ❇️ ️
lite::cv::style	Style Transfer. Contains neural style transfer now, such as FastStyleTransfer. ⚠️
lite::cv::matting	Image Matting. Object and Human matting. ❇️ ️
lite::cv::colorization	Colorization. Make Gray image become RGB. ⚠️
lite::cv::resolution	Super Resolution. ⚠️

Lite.Ai.ToolKit's Classes and Pretrained Files.

Correspondence between the classes in Lite.AI.ToolKit and pretrained model files can be found at lite.ai.toolkit.hub.onnx.md. For examples, the pretrained model files for lite::cv::detection::YoloV5 and lite::cv::detection::YoloX are listed as follows.

Class	Pretrained ONNX Files	Rename or Converted From (Repo)	Size
lite::cv::detection::YoloV5	yolov5l.onnx	yolov5 (🔥🔥💥↑)	188Mb
lite::cv::detection::YoloV5	yolov5m.onnx	yolov5 (🔥🔥💥↑)	85Mb
lite::cv::detection::YoloV5	yolov5s.onnx	yolov5 (🔥🔥💥↑)	29Mb
lite::cv::detection::YoloV5	yolov5x.onnx	yolov5 (🔥🔥💥↑)	351Mb
lite::cv::detection::YoloX	yolox_x.onnx	YOLOX (🔥🔥!!↑)	378Mb
lite::cv::detection::YoloX	yolox_l.onnx	YOLOX (🔥🔥!!↑)	207Mb
lite::cv::detection::YoloX	yolox_m.onnx	YOLOX (🔥🔥!!↑)	97Mb
lite::cv::detection::YoloX	yolox_s.onnx	YOLOX (🔥🔥!!↑)	34Mb
lite::cv::detection::YoloX	yolox_tiny.onnx	YOLOX (🔥🔥!!↑)	19Mb
lite::cv::detection::YoloX	yolox_nano.onnx	YOLOX (🔥🔥!!↑)	3.5Mb

It means that you can load the the any one yolov5*.onnx and yolox_*.onnx according to your application through the same Lite.AI.ToolKit's classes, such as YoloV5, YoloX, etc.

auto *yolov5 = new lite::cv::detection::YoloV5("yolov5x.onnx");  // for server
auto *yolov5 = new lite::cv::detection::YoloV5("yolov5l.onnx"); 
auto *yolov5 = new lite::cv::detection::YoloV5("yolov5m.onnx");  
auto *yolov5 = new lite::cv::detection::YoloV5("yolov5s.onnx");  // for mobile device 
auto *yolox = new lite::cv::detection::YoloX("yolox_x.onnx");  
auto *yolox = new lite::cv::detection::YoloX("yolox_l.onnx");  
auto *yolox = new lite::cv::detection::YoloX("yolox_m.onnx");  
auto *yolox = new lite::cv::detection::YoloX("yolox_s.onnx");  
auto *yolox = new lite::cv::detection::YoloX("yolox_tiny.onnx");  
auto *yolox = new lite::cv::detection::YoloX("yolox_nano.onnx");  // 3.5Mb only !

🔑️ How to download Model Zoo from Docker Hub?

• Firstly, pull the image from docker hub.

  docker pull qyjdefdocker/lite.ai.toolkit-mnn-hub:v0.1.22.01.08 # (11G)
  docker pull qyjdefdocker/lite.ai.toolkit-ncnn-hub:v0.1.22.01.08 # (9G)
  docker pull qyjdefdocker/lite.ai.toolkit-tnn-hub:v0.1.22.01.08 # (11G)
  docker pull qyjdefdocker/lite.ai.toolkit-onnx-hub:v0.1.22.01.08 # (28G)

• Secondly, run the container with local share dir using docker run -idt xxx. A minimum example will show you as follows.
  • make a share dir in your local device.

  mkdir share # any name is ok.

  • write run_mnn_docker_hub.sh script like:

  #!/bin/bash  
  PORT1=6072
  PORT2=6084
  SERVICE_DIR=/Users/xxx/Desktop/your-path-to/share
  CONRAINER_DIR=/home/hub/share
  CONRAINER_NAME=mnn_docker_hub_d
  
  docker run -idt -p ${PORT2}:${PORT1} -v ${SERVICE_DIR}:${CONRAINER_DIR} --shm-size=16gb --name ${CONRAINER_NAME} qyjdefdocker/lite.ai.toolkit-mnn-hub:v0.1.22.01.08
  

• Finally, copy the model weights from /home/hub/mnn/cv to your local share dir.

  # activate mnn docker.
  sh ./run_mnn_docker_hub.sh
  docker exec -it mnn_docker_hub_d /bin/bash
  # copy the models to the share dir.
  cd /home/hub 
  cp -rf mnn/cv share/

Model Hubs

The pretrained and converted ONNX files provide by lite.ai.toolkit are listed as follows. Also, see Model Zoo and ONNX Hub, MNN Hub, TNN Hub, NCNN Hub for more details.

6. Examples.

More examples can be found at examples.

Example0: Object Detection using YOLOv5. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/yolov5s.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_yolov5_1.jpg";
  std::string save_img_path = "../../../logs/test_lite_yolov5_1.jpg";

  auto *yolov5 = new lite::cv::detection::YoloV5(onnx_path); 
  std::vector<lite::types::Boxf> detected_boxes;
  cv::Mat img_bgr = cv::imread(test_img_path);
  yolov5->detect(img_bgr, detected_boxes);
  
  lite::utils::draw_boxes_inplace(img_bgr, detected_boxes);
  cv::imwrite(save_img_path, img_bgr);  
  
  delete yolov5;
}

The output is:

Or you can use Newest 🔥🔥 ! YOLO series's detector YOLOX or YoloR. They got the similar results.

More classes for general object detection (80 classes, COCO).

auto *detector = new lite::cv::detection::YoloX(onnx_path);  // Newest YOLO detector !!! 2021-07
auto *detector = new lite::cv::detection::YoloV4(onnx_path); 
auto *detector = new lite::cv::detection::YoloV3(onnx_path); 
auto *detector = new lite::cv::detection::TinyYoloV3(onnx_path); 
auto *detector = new lite::cv::detection::SSD(onnx_path); 
auto *detector = new lite::cv::detection::YoloV5(onnx_path); 
auto *detector = new lite::cv::detection::YoloR(onnx_path);  // Newest YOLO detector !!! 2021-05
auto *detector = new lite::cv::detection::TinyYoloV4VOC(onnx_path); 
auto *detector = new lite::cv::detection::TinyYoloV4COCO(onnx_path); 
auto *detector = new lite::cv::detection::ScaledYoloV4(onnx_path); 
auto *detector = new lite::cv::detection::EfficientDet(onnx_path); 
auto *detector = new lite::cv::detection::EfficientDetD7(onnx_path); 
auto *detector = new lite::cv::detection::EfficientDetD8(onnx_path); 
auto *detector = new lite::cv::detection::YOLOP(onnx_path);
auto *detector = new lite::cv::detection::NanoDet(onnx_path); // Super fast and tiny!
auto *detector = new lite::cv::detection::NanoDetPlus(onnx_path); // Super fast and tiny! 2021/12/25
auto *detector = new lite::cv::detection::NanoDetEfficientNetLite(onnx_path); // Super fast and tiny!
auto *detector = new lite::cv::detection::YoloV5_V_6_0(onnx_path); 
auto *detector = new lite::cv::detection::YoloV5_V_6_1(onnx_path); 
auto *detector = new lite::cv::detection::YoloX_V_0_1_1(onnx_path);  // Newest YOLO detector !!! 2021-07
auto *detector = new lite::cv::detection::YOLOv6(onnx_path);  // Newest 2022 YOLO detector !!!

---

Example1: Video Matting using RobustVideoMatting2021🔥🔥🔥. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/rvm_mobilenetv3_fp32.onnx";
  std::string video_path = "../../../examples/lite/resources/test_lite_rvm_0.mp4";
  std::string output_path = "../../../logs/test_lite_rvm_0.mp4";
  std::string background_path = "../../../examples/lite/resources/test_lite_matting_bgr.jpg";
  
  auto *rvm = new lite::cv::matting::RobustVideoMatting(onnx_path, 16); // 16 threads
  std::vector<lite::types::MattingContent> contents;
  
  // 1. video matting.
  cv::Mat background = cv::imread(background_path);
  rvm->detect_video(video_path, output_path, contents, false, 0.4f,
                    20, true, true, background);
  
  delete rvm;
}

The output is:

More classes for matting (image matting, video matting, trimap/mask-free, trimap/mask-based)

auto *matting = new lite::cv::matting::RobustVideoMatting:(onnx_path);  //  WACV 2022.
auto *matting = new lite::cv::matting::MGMatting(onnx_path); // CVPR 2021
auto *matting = new lite::cv::matting::MODNet(onnx_path); // AAAI 2022
auto *matting = new lite::cv::matting::MODNetDyn(onnx_path); // AAAI 2022 Dynamic Shape Inference.
auto *matting = new lite::cv::matting::BackgroundMattingV2(onnx_path); // CVPR 2020 
auto *matting = new lite::cv::matting::BackgroundMattingV2Dyn(onnx_path); // CVPR 2020 Dynamic Shape Inference.
auto *matting = new lite::cv::matting::MobileHumanMatting(onnx_path); // 3Mb only !!!

---

Example2: 1000 Facial Landmarks Detection using FaceLandmarks1000. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/FaceLandmark1000.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_face_landmarks_0.png";
  std::string save_img_path = "../../../logs/test_lite_face_landmarks_1000.jpg";
    
  auto *face_landmarks_1000 = new lite::cv::face::align::FaceLandmark1000(onnx_path);

  lite::types::Landmarks landmarks;
  cv::Mat img_bgr = cv::imread(test_img_path);
  face_landmarks_1000->detect(img_bgr, landmarks);
  lite::utils::draw_landmarks_inplace(img_bgr, landmarks);
  cv::imwrite(save_img_path, img_bgr);
  
  delete face_landmarks_1000;
}

The output is:

More classes for face alignment (68 points, 98 points, 106 points, 1000 points)

auto *align = new lite::cv::face::align::PFLD(onnx_path);  // 106 landmarks, 1.0Mb only!
auto *align = new lite::cv::face::align::PFLD98(onnx_path);  // 98 landmarks, 4.8Mb only!
auto *align = new lite::cv::face::align::PFLD68(onnx_path);  // 68 landmarks, 2.8Mb only!
auto *align = new lite::cv::face::align::MobileNetV268(onnx_path);  // 68 landmarks, 9.4Mb only!
auto *align = new lite::cv::face::align::MobileNetV2SE68(onnx_path);  // 68 landmarks, 11Mb only!
auto *align = new lite::cv::face::align::FaceLandmark1000(onnx_path);  // 1000 landmarks, 2.0Mb only!
auto *align = new lite::cv::face::align::PIPNet98(onnx_path);  // 98 landmarks, CVPR2021!
auto *align = new lite::cv::face::align::PIPNet68(onnx_path);  // 68 landmarks, CVPR2021!
auto *align = new lite::cv::face::align::PIPNet29(onnx_path);  // 29 landmarks, CVPR2021!
auto *align = new lite::cv::face::align::PIPNet19(onnx_path);  // 19 landmarks, CVPR2021!

---

Example3: Colorization using colorization. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/eccv16-colorizer.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_colorizer_1.jpg";
  std::string save_img_path = "../../../logs/test_lite_eccv16_colorizer_1.jpg";
  
  auto *colorizer = new lite::cv::colorization::Colorizer(onnx_path);
  
  cv::Mat img_bgr = cv::imread(test_img_path);
  lite::types::ColorizeContent colorize_content;
  colorizer->detect(img_bgr, colorize_content);
  
  if (colorize_content.flag) cv::imwrite(save_img_path, colorize_content.mat);
  delete colorizer;
}

The output is:

More classes for colorization (gray to rgb)

auto *colorizer = new lite::cv::colorization::Colorizer(onnx_path);

---

Example4: Face Recognition using ArcFace. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/ms1mv3_arcface_r100.onnx";
  std::string test_img_path0 = "../../../examples/lite/resources/test_lite_faceid_0.png";
  std::string test_img_path1 = "../../../examples/lite/resources/test_lite_faceid_1.png";
  std::string test_img_path2 = "../../../examples/lite/resources/test_lite_faceid_2.png";

  auto *glint_arcface = new lite::cv::faceid::GlintArcFace(onnx_path);

  lite::types::FaceContent face_content0, face_content1, face_content2;
  cv::Mat img_bgr0 = cv::imread(test_img_path0);
  cv::Mat img_bgr1 = cv::imread(test_img_path1);
  cv::Mat img_bgr2 = cv::imread(test_img_path2);
  glint_arcface->detect(img_bgr0, face_content0);
  glint_arcface->detect(img_bgr1, face_content1);
  glint_arcface->detect(img_bgr2, face_content2);

  if (face_content0.flag && face_content1.flag && face_content2.flag)
  {
    float sim01 = lite::utils::math::cosine_similarity<float>(
        face_content0.embedding, face_content1.embedding);
    float sim02 = lite::utils::math::cosine_similarity<float>(
        face_content0.embedding, face_content2.embedding);
    std::cout << "Detected Sim01: " << sim  << " Sim02: " << sim02 << std::endl;
  }

  delete glint_arcface;
}

The output is:

Detected Sim01: 0.721159 Sim02: -0.0626267

More classes for face recognition (face id vector extract)

auto *recognition = new lite::cv::faceid::GlintCosFace(onnx_path);  // DeepGlint(insightface)
auto *recognition = new lite::cv::faceid::GlintArcFace(onnx_path);  // DeepGlint(insightface)
auto *recognition = new lite::cv::faceid::GlintPartialFC(onnx_path); // DeepGlint(insightface)
auto *recognition = new lite::cv::faceid::FaceNet(onnx_path);
auto *recognition = new lite::cv::faceid::FocalArcFace(onnx_path);
auto *recognition = new lite::cv::faceid::FocalAsiaArcFace(onnx_path);
auto *recognition = new lite::cv::faceid::TencentCurricularFace(onnx_path); // Tencent(TFace)
auto *recognition = new lite::cv::faceid::TencentCifpFace(onnx_path); // Tencent(TFace)
auto *recognition = new lite::cv::faceid::CenterLossFace(onnx_path);
auto *recognition = new lite::cv::faceid::SphereFace(onnx_path);
auto *recognition = new lite::cv::faceid::PoseRobustFace(onnx_path);
auto *recognition = new lite::cv::faceid::NaivePoseRobustFace(onnx_path);
auto *recognition = new lite::cv::faceid::MobileFaceNet(onnx_path); // 3.8Mb only !
auto *recognition = new lite::cv::faceid::CavaGhostArcFace(onnx_path);
auto *recognition = new lite::cv::faceid::CavaCombinedFace(onnx_path);
auto *recognition = new lite::cv::faceid::MobileSEFocalFace(onnx_path); // 4.5Mb only !

---

Example5: Face Detection using SCRFD 2021. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/scrfd_2.5g_bnkps_shape640x640.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_face_detector.jpg";
  std::string save_img_path = "../../../logs/test_lite_scrfd.jpg";
  
  auto *scrfd = new lite::cv::face::detect::SCRFD(onnx_path);
  
  std::vector<lite::types::BoxfWithLandmarks> detected_boxes;
  cv::Mat img_bgr = cv::imread(test_img_path);
  scrfd->detect(img_bgr, detected_boxes);
  
  lite::utils::draw_boxes_with_landmarks_inplace(img_bgr, detected_boxes);
  cv::imwrite(save_img_path, img_bgr);
  
  delete scrfd;
}

The output is:

More classes for face detection (super fast face detection)

auto *detector = new lite::face::detect::UltraFace(onnx_path);  // 1.1Mb only !
auto *detector = new lite::face::detect::FaceBoxes(onnx_path);  // 3.8Mb only ! 
auto *detector = new lite::face::detect::FaceBoxesv2(onnx_path);  // 4.0Mb only ! 
auto *detector = new lite::face::detect::RetinaFace(onnx_path);  // 1.6Mb only ! CVPR2020
auto *detector = new lite::face::detect::SCRFD(onnx_path);  // 2.5Mb only ! CVPR2021, Super fast and accurate!!
auto *detector = new lite::face::detect::YOLO5Face(onnx_path);  // 2021, Super fast and accurate!!
auto *detector = new lite::face::detect::YOLOv5BlazeFace(onnx_path);  // 2021, Super fast and accurate!!

---

Example6: Object Segmentation using DeepLabV3ResNet101. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/deeplabv3_resnet101_coco.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_deeplabv3_resnet101.png";
  std::string save_img_path = "../../../logs/test_lite_deeplabv3_resnet101.jpg";

  auto *deeplabv3_resnet101 = new lite::cv::segmentation::DeepLabV3ResNet101(onnx_path, 16); // 16 threads

  lite::types::SegmentContent content;
  cv::Mat img_bgr = cv::imread(test_img_path);
  deeplabv3_resnet101->detect(img_bgr, content);

  if (content.flag)
  {
    cv::Mat out_img;
    cv::addWeighted(img_bgr, 0.2, content.color_mat, 0.8, 0., out_img);
    cv::imwrite(save_img_path, out_img);
    if (!content.names_map.empty())
    {
      for (auto it = content.names_map.begin(); it != content.names_map.end(); ++it)
      {
        std::cout << it->first << " Name: " << it->second << std::endl;
      }
    }
  }
  delete deeplabv3_resnet101;
}

The output is:

More classes for object segmentation (general objects segmentation)

auto *segment = new lite::cv::segmentation::FCNResNet101(onnx_path);
auto *segment = new lite::cv::segmentation::DeepLabV3ResNet101(onnx_path);

---

Example7: Age Estimation using SSRNet . Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/ssrnet.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_ssrnet.jpg";
  std::string save_img_path = "../../../logs/test_lite_ssrnet.jpg";

  auto *ssrnet = new lite::cv::face::attr::SSRNet(onnx_path);

  lite::types::Age age;
  cv::Mat img_bgr = cv::imread(test_img_path);
  ssrnet->detect(img_bgr, age);
  lite::utils::draw_age_inplace(img_bgr, age);
  cv::imwrite(save_img_path, img_bgr);

  delete ssrnet;
}

The output is:

More classes for face attributes analysis (age, gender, emotion)

auto *attribute = new lite::cv::face::attr::AgeGoogleNet(onnx_path);  
auto *attribute = new lite::cv::face::attr::GenderGoogleNet(onnx_path); 
auto *attribute = new lite::cv::face::attr::EmotionFerPlus(onnx_path);
auto *attribute = new lite::cv::face::attr::VGG16Age(onnx_path);
auto *attribute = new lite::cv::face::attr::VGG16Gender(onnx_path);
auto *attribute = new lite::cv::face::attr::EfficientEmotion7(onnx_path); // 7 emotions, 15Mb only!
auto *attribute = new lite::cv::face::attr::EfficientEmotion8(onnx_path); // 8 emotions, 15Mb only!
auto *attribute = new lite::cv::face::attr::MobileEmotion7(onnx_path); // 7 emotions, 13Mb only!
auto *attribute = new lite::cv::face::attr::ReXNetEmotion7(onnx_path); // 7 emotions
auto *attribute = new lite::cv::face::attr::SSRNet(onnx_path); // age estimation, 190kb only!!!

---

Example8: 1000 Classes Classification using DenseNet. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/densenet121.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_densenet.jpg";

  auto *densenet = new lite::cv::classification::DenseNet(onnx_path);

  lite::types::ImageNetContent content;
  cv::Mat img_bgr = cv::imread(test_img_path);
  densenet->detect(img_bgr, content);
  if (content.flag)
  {
    const unsigned int top_k = content.scores.size();
    if (top_k > 0)
    {
      for (unsigned int i = 0; i < top_k; ++i)
        std::cout << i + 1
                  << ": " << content.labels.at(i)
                  << ": " << content.texts.at(i)
                  << ": " << content.scores.at(i)
                  << std::endl;
    }
  }
  delete densenet;
}

The output is:

More classes for image classification (1000 classes)

auto *classifier = new lite::cv::classification::EfficientNetLite4(onnx_path);  
auto *classifier = new lite::cv::classification::ShuffleNetV2(onnx_path); // 8.7Mb only!
auto *classifier = new lite::cv::classification::GhostNet(onnx_path);
auto *classifier = new lite::cv::classification::HdrDNet(onnx_path);
auto *classifier = new lite::cv::classification::IBNNet(onnx_path);
auto *classifier = new lite::cv::classification::MobileNetV2(onnx_path); // 13Mb only!
auto *classifier = new lite::cv::classification::ResNet(onnx_path); 
auto *classifier = new lite::cv::classification::ResNeXt(onnx_path);

---

Example9: Head Pose Estimation using FSANet. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/fsanet-var.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_fsanet.jpg";
  std::string save_img_path = "../../../logs/test_lite_fsanet.jpg";

  auto *fsanet = new lite::cv::face::pose::FSANet(onnx_path);
  cv::Mat img_bgr = cv::imread(test_img_path);
  lite::types::EulerAngles euler_angles;
  fsanet->detect(img_bgr, euler_angles);
  
  if (euler_angles.flag)
  {
    lite::utils::draw_axis_inplace(img_bgr, euler_angles);
    cv::imwrite(save_img_path, img_bgr);
    std::cout << "yaw:" << euler_angles.yaw << " pitch:" << euler_angles.pitch << " row:" << euler_angles.roll << std::endl;
  }
  delete fsanet;
}

The output is:

More classes for head pose estimation (euler angle, yaw, pitch, roll)

auto *pose = new lite::cv::face::pose::FSANet(onnx_path); // 1.2Mb only!

---

Example10: Style Transfer using FastStyleTransfer. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/style-candy-8.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_fast_style_transfer.jpg";
  std::string save_img_path = "../../../logs/test_lite_fast_style_transfer_candy.jpg";
  
  auto *fast_style_transfer = new lite::cv::style::FastStyleTransfer(onnx_path);
 
  lite::types::StyleContent style_content;
  cv::Mat img_bgr = cv::imread(test_img_path);
  fast_style_transfer->detect(img_bgr, style_content);

  if (style_content.flag) cv::imwrite(save_img_path, style_content.mat);
  delete fast_style_transfer;
}

The output is:

More classes for style transfer (neural style transfer, others)

auto *transfer = new lite::cv::style::FastStyleTransfer(onnx_path); // 6.4Mb only

---

Example11: Human Head Segmentation using HeadSeg. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/minivision_head_seg.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_head_seg.png";
  std::string save_img_path = "../../../logs/test_lite_head_seg.jpg";

  auto *head_seg = new lite::cv::segmentation::HeadSeg(onnx_path, 4); // 4 threads

  lite::types::HeadSegContent content;
  cv::Mat img_bgr = cv::imread(test_img_path);
  head_seg->detect(img_bgr, content);
  if (content.flag) cv::imwrite(save_img_path, content.mask * 255.f);

  delete head_seg;
}

The output is:

More classes for human segmentation (head, portrait, hair, others)

auto *segment = new lite::cv::segmentation::HeadSeg(onnx_path); // 31Mb
auto *segment = new lite::cv::segmentation::FastPortraitSeg(onnx_path); // <= 400Kb !!! 
auto *segment = new lite::cv::segmentation::PortraitSegSINet(onnx_path); // <= 380Kb !!!
auto *segment = new lite::cv::segmentation::PortraitSegExtremeC3Net(onnx_path); // <= 180Kb !!! Extreme Tiny !!!
auto *segment = new lite::cv::segmentation::FaceHairSeg(onnx_path); // 18M
auto *segment = new lite::cv::segmentation::HairSeg(onnx_path); // 18M
auto *segment = new lite::cv::segmentation::MobileHairSeg(onnx_path); // 14M

---

Example12: Photo transfer to Cartoon Photo2Cartoon. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string head_seg_onnx_path = "../../../hub/onnx/cv/minivision_head_seg.onnx";
  std::string cartoon_onnx_path = "../../../hub/onnx/cv/minivision_female_photo2cartoon.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_female_photo2cartoon.jpg";
  std::string save_mask_path = "../../../logs/test_lite_female_photo2cartoon_seg.jpg";
  std::string save_cartoon_path = "../../../logs/test_lite_female_photo2cartoon_cartoon.jpg";

  auto *head_seg = new lite::cv::segmentation::HeadSeg(head_seg_onnx_path, 4); // 4 threads
  auto *female_photo2cartoon = new lite::cv::style::FemalePhoto2Cartoon(cartoon_onnx_path, 4); // 4 threads

  lite::types::HeadSegContent head_seg_content;
  cv::Mat img_bgr = cv::imread(test_img_path);
  head_seg->detect(img_bgr, head_seg_content);

  if (head_seg_content.flag && !head_seg_content.mask.empty())
  {
    cv::imwrite(save_mask_path, head_seg_content.mask * 255.f);
    // Female Photo2Cartoon Style Transfer
    lite::types::FemalePhoto2CartoonContent female_cartoon_content;
    female_photo2cartoon->detect(img_bgr, head_seg_content.mask, female_cartoon_content);
    
    if (female_cartoon_content.flag && !female_cartoon_content.cartoon.empty())
      cv::imwrite(save_cartoon_path, female_cartoon_content.cartoon);
  }

  delete head_seg;
  delete female_photo2cartoon;
}

The output is:

More classes for photo style transfer.

auto *transfer = new lite::cv::style::FemalePhoto2Cartoon(onnx_path);

---

Example13: Face Parsing using FaceParsing. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/face_parsing_512x512.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_face_parsing.png";
  std::string save_img_path = "../../../logs/test_lite_face_parsing_bisenet.jpg";

  auto *face_parsing_bisenet = new lite::cv::segmentation::FaceParsingBiSeNet(onnx_path, 8); // 8 threads

  lite::types::FaceParsingContent content;
  cv::Mat img_bgr = cv::imread(test_img_path);
  face_parsing_bisenet->detect(img_bgr, content);

  if (content.flag && !content.merge.empty())
    cv::imwrite(save_img_path, content.merge);
  
  delete face_parsing_bisenet;
}

The output is:

More classes for face parsing (hair, eyes, nose, mouth, others)

auto *segment = new lite::cv::segmentation::FaceParsingBiSeNet(onnx_path); // 50Mb
auto *segment = new lite::cv::segmentation::FaceParsingBiSeNetDyn(onnx_path); // Dynamic Shape Inference.

7. License.

The code of Lite.Ai.ToolKit is released under the GPL-3.0 License.

8. References.

Many thanks to these following projects. All the Lite.AI.ToolKit's models are sourced from these repos.

• RobustVideoMatting (🔥🔥🔥new!!↑)
• nanodet (🔥🔥🔥↑)
• YOLOX (🔥🔥🔥new!!↑)
• YOLOP (🔥🔥new!!↑)
• YOLOR (🔥🔥new!!↑)
• ScaledYOLOv4 (🔥🔥🔥↑)
• insightface (🔥🔥🔥↑)
• yolov5 (🔥🔥💥↑)
• TFace (🔥🔥↑)
• YOLOv4-pytorch (🔥🔥🔥↑)
• Ultra-Light-Fast-Generic-Face-Detector-1MB (🔥🔥🔥↑)

Expand for More References.

• headpose-fsanet-pytorch (🔥↑)
• pfld_106_face_landmarks (🔥🔥↑)
• onnx-models (🔥🔥🔥↑)
• SSR_Net_Pytorch (🔥↑)
• colorization (🔥🔥🔥↑)
• SUB_PIXEL_CNN (🔥↑)
• torchvision (🔥🔥🔥↑)
• facenet-pytorch (🔥↑)
• face.evoLVe.PyTorch (🔥🔥🔥↑)
• center-loss.pytorch (🔥🔥↑)
• sphereface_pytorch (🔥🔥↑)
• DREAM (🔥🔥↑)
• MobileFaceNet_Pytorch (🔥🔥↑)
• cavaface.pytorch (🔥🔥↑)
• CurricularFace (🔥🔥↑)
• face-emotion-recognition (🔥↑)
• face_recognition.pytorch (🔥🔥↑)
• PFLD-pytorch (🔥🔥↑)
• pytorch_face_landmark (🔥🔥↑)
• FaceLandmark1000 (🔥🔥↑)
• Pytorch_Retinaface (🔥🔥🔥↑)
• FaceBoxes (🔥🔥↑)

9. Compilation Options.

In addition, MNN, NCNN and TNN support for some models will be added in the future, but due to operator compatibility and some other reasons, it is impossible to ensure that all models supported by ONNXRuntime C++ can run through MNN, NCNN and TNN. So, if you want to use all the models supported by this repo and don't care about the performance gap of 1~2ms, just let ONNXRuntime as default inference engine for this repo. However, you can follow the steps below if you want to build with MNN, NCNN or TNN support.

• change the build.sh with DENABLE_MNN=ON,DENABLE_NCNN=ON or DENABLE_TNN=ON, such as

cd build && cmake \
  -DCMAKE_BUILD_TYPE=MinSizeRel \
  -DINCLUDE_OPENCV=ON \   # Whether to package OpenCV into lite.ai.toolkit, default ON; otherwise, you need to setup OpenCV yourself.
  -DENABLE_MNN=ON \       # Whether to build with MNN,  default OFF, only some models are supported now.
  -DENABLE_NCNN=OFF \     # Whether to build with NCNN, default OFF, only some models are supported now.
  -DENABLE_TNN=OFF \      # Whether to build with TNN,  default OFF, only some models are supported now.
  .. && make -j8

• use the MNN, NCNN or TNN version interface, see demo, such as

auto *nanodet = new lite::mnn::cv::detection::NanoDet(mnn_path);
auto *nanodet = new lite::tnn::cv::detection::NanoDet(proto_path, model_path);
auto *nanodet = new lite::ncnn::cv::detection::NanoDet(param_path, bin_path);

10. Contribute

How to add your own models and become a contributor? See CONTRIBUTING.zh.md.

11. Many Thanks !!! 🤗🎉🎉

• Windows10 VS2019 CUDA 11.1 Build Docs (@zhanghongyong123456)
• Linux Build Docs (@lee1221ee)
• Some Windows10 Bugs Fixed (@ysc3839, @AvenSun)