lite.ai.toolkit: A C++ repository from cocoa-chen

Lite.AI.ToolKit 🚀🚀🌟: A lite C++ toolkit of awesome AI models.

English | 中文文档 | MacOS | Linux | Windows

Lite.AI.ToolKit 🚀🚀🌟: A lite C++ toolkit of awesome AI models which contains 70+ models now. It's a collection of personal interests. Such as RVM, YOLOX, YOLOP, YOLOR, YoloV5, DeepLabV3, ArcFace, etc. emmm😞 ... it's not perfect yet. For now, let's regard it as a large collection of application cases for inference engines. Lite.AI.ToolKit based on ONNXRuntime C++ by default. I do have plans to reimplement it with NCNN, MNN and TNN, some models are already supported. Currently, I mainly consider its ease of use. Developers who need higher performance can make new optimizations based on the C++ implementation and ONNX files provided by this repo~ Welcome to open a new PR~ 👏👋, if you want to add a new model to this repo.

Core 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 10+ modules and 70+ famous models with 300+ frozen pretrained .onnx/.mnn/.param&bin(ncnn)/.tnnmodel&tnnproto files now, such as object detection, face detection, face recognition, segmentation, matting, etc. See Model Zoo and lite.ai.toolkit.hub.onnx.md.

❤️ Star 🌟👆🏻 this repo if it does any helps to you ~ 🙃🤪🍀

Important Notes !!!

🔥 (20211002) Added NanoDet for object detection. ⚡ Super fast and tiny! 1.1Mb only! See demo.
🔥 (20210920) Added RobustVideoMatting as lite::cv::matting::RobustVideoMatting ! See demo.

🔥 (20210915) Added YOLOP Panoptic 🚗 Perception as lite::cv::detection::YOLOP ! See demo.

✅ (20210807) Added YoloR ! Use it through lite::cv::detection::YoloR syntax ! See demo.
✅ (20210731) Added RetinaFace-CVPR2020 for face detection, 1.6Mb only! See demo.
🔥 (20210721) Added YOLOX! Use it through lite::cv::detection::YoloX syntax ! See demo.

Expand for More Notes.

More Notes !!!

✅ (20210815) Added EfficientDet for object detection! See demo.
✅ (20210808) Added ScaledYoloV4 for object detection! See demo.
✅ (20210807) Added TinyYoloV4VOC for object detection! See demo.
✅ (20210807) Added TinyYoloV4COCO for object detection! See demo.
✅ (20210722) Update lite.ai.toolkit.hub.onnx.md ! Lite.AI.Toolkit contains 70+ AI models with 150+ .onnx files now.
⚠️ (20210802) Added GPU Compatibility for CUDAExecutionProvider. See issue#10.
⚠️ (20210801) fixed issue#9 YOLOX inference error for non-square shape. See yolox.cpp.
✅ (20210801) Added FaceBoxes for face detection! See demo.
✅ (20210727) Added MobileNetV2SE68、PFLD68 for 68 facial landmarks detection! See demo.
✅ (20210726) Added PFLD98 for 98 facial landmarks detection! See demo.

1. Build Lite.AI.ToolKit 🚀🚀🌟

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. Click ▶️ will show you the docs how to build Lite.AI.ToolKit 🚀🚀🌟 for Linux and Windows.

⚠️ 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 directory. Please reference the build-docs¹ for third_party.

lite.ai.toolkit/lib

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

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 downlod 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.

    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.

GPU Compatibility: See issue#10.
To link Lite.AI.ToolKit, you can follow the CMakeLists.txt listed belows.

cmake_minimum_required(VERSION 3.17)
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.

Expand for more details of How to link the shared lib of Lite.AI.ToolKit?

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. Just like:

cmake_minimum_required(VERSION 3.17)
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
        ncnn
        ${OpenCV_LIBS})  # link lite.ai.toolkit & other libs.

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 lite.ai.toolkit.demo.

2. Model Zoo.

Lite.AI.ToolKit contains 70+ AI models with 300+ frozen pretrained .onnx/.mnn/.param&bin(ncnn)/.tnnmodel&tnnproto 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.

Expand Details for Namespace and Lite.AI.ToolKit modules.

Namespace and Lite.AI.ToolKit modules.

Namepace	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::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 !

Downloads:
Note, for Google Drive, I can not upload all the *.onnx files because of the storage limitation (15G).
- ONNX files 👉 Baidu Drive code: 8gin && Google Drive. See lite.ai.toolkit.hub.onnx.md
- MNN files 👉 Baidu Drive code: 9v63 && Google Drive(Wait). See lite.ai.toolkit.hub.mnn.md
- NCNN files 👉 Baidu Drive code: sc7f && Google Drive(Wait). See lite.ai.toolkit.hub.ncnn.md
- TNN files 👉 Baidu Drive code: 6o6k && Google Drive(Wait). See lite.ai.toolkit.hub.tnn.md
Object Detection.

Class	Size	From	Awesome	Type	State	Usage
YoloV5	28M	yolov5	🔥🔥💥↑	detection	✅	demo
YoloV3	236M	onnx-models	🔥🔥🔥↑	detection	✅	demo
TinyYoloV3	33M	onnx-models	🔥🔥🔥↑	detection	✅	demo
YoloV4	176M	YOLOv4...	🔥🔥🔥↑	detection	✅	demo
SSD	76M	onnx-models	🔥🔥🔥↑	detection	✅	demo
SSDMobileNetV1	27M	onnx-models	🔥🔥🔥↑	detection	✅	demo
YoloX	3.5M	YOLOX	🔥🔥🔥↑	detection	✅	demo
TinyYoloV4VOC	22M	yolov4-tiny...	🔥🔥↑	detection	✅	demo
TinyYoloV4COCO	22M	yolov4-tiny...	🔥🔥↑	detection	✅	demo
YoloR	39M	yolor	🔥🔥↑	detection	✅	demo
ScaledYoloV4	270M	ScaledYOLOv4	🔥🔥🔥↑	detection	✅	demo
EfficientDet	15M	...EfficientDet...	🔥🔥🔥↑	detection	✅	demo
EfficientDetD7	220M	...EfficientDet...	🔥🔥🔥↑	detection	✅	demo
EfficientDetD8	322M	...EfficientDet...	🔥🔥🔥↑	detection	✅	demo
YOLOP	30M	YOLOP	🔥🔥↑	detection	✅	demo
NanoDet	1.1M	nanodet	🔥🔥🔥↑	detection	✅	demo
NanoDetEfficientNetLite	12M	nanodet	🔥🔥🔥↑	detection	✅	demo

Class	Size	From	Awesome	Type	State	Usage
YoloX	3.5M	YOLOX	🔥🔥🔥↑	detection	✅	demo
YOLOP	30M	YOLOP	🔥🔥↑	detection	✅	demo
NanoDet	1.1M	nanodet	🔥🔥🔥↑	detection	✅	demo
NanoDetEfficientNetLite	12M	nanodet	🔥🔥🔥↑	detection	✅	demo

Class	Size	From	Awesome	Type	State	Usage
YoloX	3.5M	YOLOX	🔥🔥🔥↑	detection	✅	demo
NanoDet	1.1M	nanodet	🔥🔥🔥↑	detection	✅	demo
NanoDetEfficientNetLite	12M	nanodet	🔥🔥🔥↑	detection	✅	demo
NanoDetDepreciated	1.1M	nanodet	🔥🔥🔥↑	detection	✅	demo
NanoDetEfficientNetLiteD...	12M	nanodet	🔥🔥🔥↑	detection	✅	demo

Class	Size	From	Awesome	Type	State	Usage
YoloX	3.5M	YOLOX	🔥🔥🔥↑	detection	✅	demo
YOLOP	30M	YOLOP	🔥🔥↑	detection	✅	demo
NanoDet	1.1M	nanodet	🔥🔥🔥↑	detection	✅	demo
NanoDetEfficientNetLite	12M	nanodet	🔥🔥🔥↑	detection	✅	demo

Face Recognition.

Class	Size	From	Awesome	Type	State	Usage
GlintArcFace	92M	insightface	🔥🔥🔥↑	faceid	✅	demo
GlintCosFace	92M	insightface	🔥🔥🔥↑	faceid	✅	demo
GlintPartialFC	170M	insightface	🔥🔥🔥↑	faceid	✅	demo
FaceNet	89M	facenet...	🔥🔥🔥↑	faceid	✅	demo
FocalArcFace	166M	face.evoLVe...	🔥🔥🔥↑	faceid	✅	demo
FocalAsiaArcFace	166M	face.evoLVe...	🔥🔥🔥↑	faceid	✅	demo
TencentCurricularFace	249M	TFace	🔥🔥↑	faceid	✅	demo
TencentCifpFace	130M	TFace	🔥🔥↑	faceid	✅	demo
CenterLossFace	280M	center-loss...	🔥🔥↑	faceid	✅	demo
SphereFace	80M	sphere...	🔥🔥↑	faceid	✅️	demo
PoseRobustFace	92M	DREAM	🔥🔥↑	faceid	✅️	demo
NaivePoseRobustFace	43M	DREAM	🔥🔥↑	faceid	✅️	demo
MobileFaceNet	3.8M	MobileFace...	🔥🔥↑	faceid	✅	demo
CavaGhostArcFace	15M	cavaface...	🔥🔥↑	faceid	✅	demo
CavaCombinedFace	250M	cavaface...	🔥🔥↑	faceid	✅	demo
MobileSEFocalFace	4.5M	face_recog...	🔥🔥↑	faceid	✅	demo

Matting.

Class	Size	From	Awesome	File	Type	State	Usage
RobustVideoMatting	14M	RobustVideoMatting	🔥🔥🔥↑		matting	✅	demo

Class	Size	From	Awesome	File	Type	State	Usage
RobustVideoMatting	14M	RobustVideoMatting	🔥🔥🔥↑		matting	✅	demo

Class	Size	From	Awesome	File	Type	State	Usage
RobustVideoMatting	14M	RobustVideoMatting	🔥🔥🔥↑		matting	⚠️	code

Class	Size	From	Awesome	File	Type	State	Usage
RobustVideoMatting	14M	RobustVideoMatting	🔥🔥🔥↑		matting	✅️	demo

⚠️ Expand More Details for Lite.AI.ToolKit's Model Zoo.

Face Detection.

Class	Size	From	Awesome	Type	State	Usage
UltraFace	1.1M	Ultra-Light...	🔥🔥🔥↑	face::detect	✅	demo
RetinaFace	1.6M	...Retinaface	🔥🔥🔥↑	face::detect	✅	demo
FaceBoxes	3.8M	FaceBoxes	🔥🔥↑	face::detect	✅	demo

Face Alignment.

Class	Size	From	Awesome	Type	State	Usage
PFLD	1.0M	pfld_106_...	🔥🔥↑	face::align	✅	demo
PFLD98	4.8M	PFLD...	🔥🔥↑	face::align	✅️	demo
MobileNetV268	9.4M	...landmark	🔥🔥↑	face::align	✅️️	demo
MobileNetV2SE68	11M	...landmark	🔥🔥↑	face::align	✅️️	demo
PFLD68	2.8M	...landmark	🔥🔥↑	face::align	✅️	demo
FaceLandmark1000	2.0M	FaceLandm...	🔥↑	face::align	✅️	demo

Head Pose Estimation.

Class	Size	From	Awesome	File	Type	State	Usage
FSANet	1.2M	...fsanet...	🔥↑		face::pose	✅	demo

Face Attributes.

Class	Size	From	Awesome	Type	State	Usage
AgeGoogleNet	23M	onnx-models	🔥🔥🔥↑	face::attr	✅	demo
GenderGoogleNet	23M	onnx-models	🔥🔥🔥↑	face::attr	✅	demo
EmotionFerPlus	33M	onnx-models	🔥🔥🔥↑	face::attr	✅	demo
VGG16Age	514M	onnx-models	🔥🔥🔥↑	face::attr	✅	demo
VGG16Gender	512M	onnx-models	🔥🔥🔥↑	face::attr	✅	demo
SSRNet	190K	SSR_Net...	🔥↑	face::attr	✅	demo
EfficientEmotion7	15M	face-emo...	🔥↑	face::attr	✅️	demo
EfficientEmotion8	15M	face-emo...	🔥↑	face::attr	✅	demo
MobileEmotion7	13M	face-emo...	🔥↑	face::attr	✅	demo
ReXNetEmotion7	30M	face-emo...	🔥↑	face::attr	✅	demo

Classification.

Class	Size	From	Awesome	Type	State	Usage
EfficientNetLite4	49M	onnx-models	🔥🔥🔥↑	classification	✅	demo
ShuffleNetV2	8.7M	onnx-models	🔥🔥🔥↑	classification	✅	demo
DenseNet121	30.7M	torchvision	🔥🔥🔥↑	classification	✅	demo
GhostNet	20M	torchvision	🔥🔥🔥↑	classification	✅	demo
HdrDNet	13M	torchvision	🔥🔥🔥↑	classification	✅	demo
IBNNet	97M	torchvision	🔥🔥🔥↑	classification	✅	demo
MobileNetV2	13M	torchvision	🔥🔥🔥↑	classification	✅	demo
ResNet	44M	torchvision	🔥🔥🔥↑	classification	✅	demo
ResNeXt	95M	torchvision	🔥🔥🔥↑	classification	✅	demo

Segmentation.

Class	Size	From	Awesome	File	Type	State	Usage
DeepLabV3ResNet101	232M	torchvision	🔥🔥🔥↑		segmentation	✅	demo
FCNResNet101	207M	torchvision	🔥🔥🔥↑		segmentation	✅	demo

Style Transfer.

Class	Size	From	Awesome	File	Type	State	Usage
FastStyleTransfer	6.4M	onnx-models	🔥🔥🔥↑		style	✅	demo

Colorization.

Class	Size	From	Awesome	File	Type	State	Usage
Colorizer	123M	colorization	🔥🔥🔥↑		colorization	✅	demo

Super Resolution.

Class	Size	From	Awesome	File	Type	State	Usage
SubPixelCNN	234K	...PIXEL...	🔥↑		resolution	✅	demo

3. Examples for Lite.AI.ToolKit.

More examples can be found at lite.ai.toolkit.examples. Click ▶️ will show you more examples for the specific topic you are interested in.

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.

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";
  
  auto *rvm = new lite::cv::matting::RobustVideoMatting(onnx_path, 16); // 16 threads
  std::vector<lite::types::MattingContent> contents;
  
  // 1. video matting.
  rvm->detect_video(video_path, output_path, contents, false, 0.4f);
  
  delete rvm;
}

The output is:

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:

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:

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

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

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/ultraface-rfb-640.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_ultraface.jpg";
  std::string save_img_path = "../../../logs/test_lite_ultraface.jpg";

  auto *ultraface = new lite::cv::face::detect::UltraFace(onnx_path);

  std::vector<lite::types::Boxf> detected_boxes;
  cv::Mat img_bgr = cv::imread(test_img_path);
  ultraface->detect(img_bgr, detected_boxes);
  lite::utils::draw_boxes_inplace(img_bgr, detected_boxes);
  cv::imwrite(save_img_path, img_bgr);

  delete ultraface;
}

The output is:

⚠️ Expand All Examples for Each Topic in Lite.AI.ToolKit

3.1 Expand Examples for Object Detection.

3.1 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 . They got the similar results.

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/yolox_s.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_yolox_1.jpg";
  std::string save_img_path = "../../../logs/test_lite_yolox_1.jpg";

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

The output is:

More classes for general object detection.

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::NanoDetEfficientNetLite(onnx_path); // Super fast and tiny!

3.2 Expand Examples for Face Recognition.

3.2 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.

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 !

3.3 Expand Examples for Segmentation.

3.3 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 segmentation.

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

3.4 Expand Examples for Face Attributes Analysis.

3.4 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";

  lite::cv::face::attr::SSRNet *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);
  std::cout << "Default Version Done! Detected SSRNet Age: " << age.age << std::endl;

  delete ssrnet;
}

The output is:

More classes for face attributes analysis.

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
auto *attribute = new lite::cv::face::attr::ReXNetEmotion7(onnx_path); // 7 emotions

3.5 Expand Examples for Image Classification.

3.5 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.

auto *classifier = new lite::cv::classification::EfficientNetLite4(onnx_path);  
auto *classifier = new lite::cv::classification::ShuffleNetV2(onnx_path); 
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); 
auto *classifier = new lite::cv::classification::ResNet(onnx_path); 
auto *classifier = new lite::cv::classification::ResNeXt(onnx_path);

3.6 Expand Examples for Face Detection.

3.6 Face Detection using UltraFace. Download model from Model-Zoo².

#include "lite/lite.h"

static void test_default()
{
  std::string onnx_path = "../../../hub/onnx/cv/ultraface-rfb-640.onnx";
  std::string test_img_path = "../../../examples/lite/resources/test_lite_ultraface.jpg";
  std::string save_img_path = "../../../logs/test_lite_ultraface.jpg";

  auto *ultraface = new lite::cv::face::detect::UltraFace(onnx_path);

  std::vector<lite::types::Boxf> detected_boxes;
  cv::Mat img_bgr = cv::imread(test_img_path);
  ultraface->detect(img_bgr, detected_boxes);
  lite::utils::draw_boxes_inplace(img_bgr, detected_boxes);
  cv::imwrite(save_img_path, img_bgr);

  delete ultraface;
}

The output is:

More classes for 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::RetinaFace(onnx_path);  // 1.6Mb only ! CVPR2020

3.7 Expand Examples for Colorization.

3.7 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:

3.8 Expand Examples for Head Pose Estimation.

3.8 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:

3.9 Expand Examples for Face Alignment.

3.9 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.

auto *align = new lite::cv::face::align::PFLD(onnx_path);  // 106 landmarks
auto *align = new lite::cv::face::align::PFLD98(onnx_path);  // 98 landmarks
auto *align = new lite::cv::face::align::PFLD68(onnx_path);  // 68 landmarks
auto *align = new lite::cv::face::align::MobileNetV268(onnx_path);  // 68 landmarks
auto *align = new lite::cv::face::align::MobileNetV2SE68(onnx_path);  // 68 landmarks
auto *align = new lite::cv::face::align::FaceLandmark1000(onnx_path);  // 1000 landmarks !

3.10 Expand Examples for Style Transfer.

3.10 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:

3.11 Expand Examples for Image Matting.

3.11 Video Matting using RobustVideoMatting. 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";
  
  auto *rvm = new lite::cv::matting::RobustVideoMatting(onnx_path, 16); // 16 threads
  std::vector<lite::types::MattingContent> contents;
  
  // 1. video matting.
  rvm->detect_video(video_path, output_path, contents);
  
  delete rvm;
}

The output is:

4. Lite.AI.ToolKit API Docs.

4.1 Default Version APIs.

More details of Default Version APIs can be found at api.default.md . For examples, the interface for YoloV5 is:

lite::cv::detection::YoloV5

void detect(const cv::Mat &mat, std::vector<types::Boxf> &detected_boxes, 
            float score_threshold = 0.25f, float iou_threshold = 0.45f,
            unsigned int topk = 100, unsigned int nms_type = NMS::OFFSET);

Expand for ONNXRuntime, MNN, NCNN and TNN version APIs.

4.2 ONNXRuntime Version APIs.

More details of ONNXRuntime Version APIs can be found at api.onnxruntime.md . For examples, the interface for YoloV5 is:

lite::onnxruntime::cv::detection::YoloV5

void detect(const cv::Mat &mat, std::vector<types::Boxf> &detected_boxes, 
            float score_threshold = 0.25f, float iou_threshold = 0.45f,
            unsigned int topk = 100, unsigned int nms_type = NMS::OFFSET);

4.3 MNN Version APIs.

(todo⚠️: Not implementation now, coming soon.)

lite::mnn::cv::detection::YoloV5

lite::mnn::cv::detection::YoloV4

lite::mnn::cv::detection::YoloV3

lite::mnn::cv::detection::SSD

...

4.4 NCNN Version APIs.

(todo⚠️: Not implementation now, coming soon.)

lite::ncnn::cv::detection::YoloV5

lite::ncnn::cv::detection::YoloV4

lite::ncnn::cv::detection::YoloV3

lite::ncnn::cv::detection::SSD

...

4.5 TNN Version APIs.

(todo⚠️: Not implementation now, coming soon.)

lite::tnn::cv::detection::YoloV5

lite::tnn::cv::detection::YoloV4

lite::tnn::cv::detection::YoloV3

lite::tnn::cv::detection::SSD

...

5. Other Docs.

Expand More Details for Other Docs.

5.1 Docs for ONNXRuntime.

5.2 Docs for third_party.

Other build documents for different engines and different targets will be added later.

Library	Target	Docs
OpenCV	mac-x86_64	opencv-mac-x86_64-build.zh.md
OpenCV	android-arm	opencv-static-android-arm-build.zh.md
onnxruntime	mac-x86_64	onnxruntime-mac-x86_64-build.zh.md
onnxruntime	android-arm	onnxruntime-android-arm-build.zh.md
NCNN	mac-x86_64	todo⚠️
MNN	mac-x86_64	todo⚠️
TNN	mac-x86_64	todo⚠️

6. License.

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

7. 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 (🔥🔥↑)

8. Citations.

Cite it as follows if you use Lite.AI.ToolKit.

@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}
}

9. Notification.

If there is a model you are interested in and want to be supported by Lite.AI.ToolKit🚀🚀🌟, you can fork this repo and modify TODOLIST.md, then submit a PR~ I will review this PR and try to support this model in the future, but I don’t make sure this can be done. 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, please use the implementation of ONNXRuntime version. ONNXRuntime is the default inference engine for this repo. However, you can follow the steps below if you want to build Lite.AI.ToolKit🚀🚀🌟 with MNN, NCNN or TNN support (⚠️ NOT STABLE NOW! NOT RECOMMENDED!!!🤦)

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);

cocoa-chen/lite.ai.toolkit

Lite.AI.ToolKit 🚀🚀🌟: A lite C++ toolkit of awesome AI models.

Important Notes !!!

More Notes !!!

Contents.

1. Build Lite.AI.ToolKit 🚀🚀🌟

Linux and Windows.

2. Model Zoo.

Namespace and Lite.AI.ToolKit modules.

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

3. Examples for Lite.AI.ToolKit.

Example0: Object Detection using YoloV5. Download model from Model-Zoo2.

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

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

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

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

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

3.1 Object Detection using YoloV5. Download model from Model-Zoo2.

3.2 Face Recognition using ArcFace. Download model from Model-Zoo2.

3.3 Segmentation using DeepLabV3ResNet101. Download model from Model-Zoo2.

3.4 Age Estimation using SSRNet . Download model from Model-Zoo2.

3.5 1000 Classes Classification using DenseNet. Download model from Model-Zoo2.

3.6 Face Detection using UltraFace. Download model from Model-Zoo2.

3.7 Colorization using colorization. Download model from Model-Zoo2.

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

3.9 1000 Facial Landmarks Detection using FaceLandmarks1000. Download model from Model-Zoo2.

3.10 Style Transfer using FastStyleTransfer. Download model from Model-Zoo2.

3.11 Video Matting using RobustVideoMatting. Download model from Model-Zoo2.

4. Lite.AI.ToolKit API Docs.

4.1 Default Version APIs.

4.2 ONNXRuntime Version APIs.

4.3 MNN Version APIs.

4.4 NCNN Version APIs.

4.5 TNN Version APIs.

5. Other Docs.

5.1 Docs for ONNXRuntime.

5.2 Docs for third_party.

6. License.

7. References.

8. Citations.

9. Notification.

10. Related projects.

Example0: Object Detection using YoloV5. Download model from Model-Zoo².

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

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

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

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

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

3.1 Object Detection using YoloV5. Download model from Model-Zoo².

3.2 Face Recognition using ArcFace. Download model from Model-Zoo².

3.3 Segmentation using DeepLabV3ResNet101. Download model from Model-Zoo².

3.4 Age Estimation using SSRNet . Download model from Model-Zoo².

3.5 1000 Classes Classification using DenseNet. Download model from Model-Zoo².

3.6 Face Detection using UltraFace. Download model from Model-Zoo².

3.7 Colorization using colorization. Download model from Model-Zoo².

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

3.9 1000 Facial Landmarks Detection using FaceLandmarks1000. Download model from Model-Zoo².

3.10 Style Transfer using FastStyleTransfer. Download model from Model-Zoo².

3.11 Video Matting using RobustVideoMatting. Download model from Model-Zoo².