arnoldfychen / lite.ai.toolkit

πŸ›  A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, YOLOv5, YOLOR, NanoDet, YOLOX, SCRFD, YOLOX . MNN, NCNN, TNN, ONNXRuntime, CPU/GPU.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

logo-v3

πŸ› 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 πŸŒŸπŸ‘†πŸ» this repo to support me if it does any helps to you, thanks ~ ]


English | δΈ­ζ–‡ζ–‡ζ‘£ | MacOS | Linux | Windows

Core Features πŸ‘πŸ‘‹

  • 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 with 80+ AI models and 500+ weights now.

Citations πŸŽ‰πŸŽ‰

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 βœ…

Some prebuilt lite.ai.toolkit libs for MacOS are available, you can download the libs from the release links. Further, prebuilt libs for Linux、Windows and Android will be coming soon ~ See issues#48 for more details.

Contents πŸ“–πŸ’‘

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;
}

The output is:

2. RoadMap πŸ‘πŸ‘‹

3. Important Updates!!

Date Model C++ Paper Code Awesome Type
【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

4. Supported Models Matrix

  • / = not supported now.
  • βœ… = known work and official supported now.
  • βœ”οΈ = 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 βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
YoloV3 236M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
TinyYoloV3 33M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
YoloV4 176M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
SSD 76M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
SSDMobileNetV1 27M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
YoloX 3.5M detection demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
TinyYoloV4VOC 22M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
TinyYoloV4COCO 22M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
YoloR 39M detection demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
ScaledYoloV4 270M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
EfficientDet 15M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
EfficientDetD7 220M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
EfficientDetD8 322M detection demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
YOLOP 30M detection demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
NanoDet 1.1M detection demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
NanoDetPlus 4.5M detection demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
NanoDetEffi... 12M detection demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
YoloX_V_0_1_1 3.5M detection demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
YoloV5_V_6_0 7.5M detection demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
GlintArcFace 92M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
GlintCosFace 92M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
GlintPartialFC 170M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
FaceNet 89M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
FocalArcFace 166M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
FocalAsiaArcFace 166M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
TencentCurricularFace 249M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
TencentCifpFace 130M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
CenterLossFace 280M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
SphereFace 80M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
PoseRobustFace 92M faceid demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
NaivePoseRobustFace 43M faceid demo βœ… / / / βœ… βœ”οΈ βœ”οΈ /
MobileFaceNet 3.8M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
CavaGhostArcFace 15M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
CavaCombinedFace 250M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
MobileSEFocalFace 4.5M faceid demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
RobustVideoMatting 14M matting demo βœ… βœ… / βœ… βœ… βœ”οΈ βœ”οΈ ❔
MGMatting 113M matting demo βœ… βœ… / βœ… βœ… βœ”οΈ βœ”οΈ /
UltraFace 1.1M face::detect demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
RetinaFace 1.6M face::detect demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
FaceBoxes 3.8M face::detect demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
SCRFD 2.5M face::detect demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
YOLO5Face 4.8M face::detect demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
PFLD 1.0M face::align demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
PFLD98 4.8M face::align demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
MobileNetV268 9.4M face::align demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
MobileNetV2SE68 11M face::align demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
PFLD68 2.8M face::align demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
FaceLandmark1000 2.0M face::align demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
FSANet 1.2M face::pose demo βœ… βœ… / βœ… βœ… βœ”οΈ βœ”οΈ ❔
AgeGoogleNet 23M face::attr demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
GenderGoogleNet 23M face::attr demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
EmotionFerPlus 33M face::attr demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
VGG16Age 514M face::attr demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
VGG16Gender 512M face::attr demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
SSRNet 190K face::attr demo βœ… βœ… / βœ… βœ… βœ”οΈ βœ”οΈ ❔
EfficientEmotion7 15M face::attr demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
EfficientEmotion8 15M face::attr demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
MobileEmotion7 13M face::attr demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
ReXNetEmotion7 30M face::attr demo βœ… βœ… / βœ… βœ… βœ”οΈ βœ”οΈ /
EfficientNetLite4 49M classification demo βœ… βœ… / βœ… βœ… βœ”οΈ βœ”οΈ /
ShuffleNetV2 8.7M classification demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
DenseNet121 30.7M classification demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
GhostNet 20M classification demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
HdrDNet 13M classification demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
IBNNet 97M classification demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
MobileNetV2 13M classification demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
ResNet 44M classification demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
ResNeXt 95M classification demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
DeepLabV3ResNet101 232M segmentation demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
FCNResNet101 207M segmentation demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ /
FastStyleTransfer 6.4M style demo βœ… βœ… βœ… βœ… βœ… βœ”οΈ βœ”οΈ ❔
Colorizer 123M colorization demo βœ… βœ… / βœ… βœ… βœ”οΈ βœ”οΈ /
SubPixelCNN 234K resolution demo βœ… βœ… / βœ… βœ… βœ”οΈ βœ”οΈ ❔

5. 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.
πŸ’‘ 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/(linux|windows)/*opencv* lite.ai.toolkit/lib
      cp you-path-to-downloaded-or-built-onnxruntime/lib/(linux|windows)/*onnxruntime* lite.ai.toolkit/lib
      cp you-path-to-downloaded-or-built-MNN/lib/(linux|windows)/*MNN* lite.ai.toolkit/lib
      cp you-path-to-downloaded-or-built-ncnn/lib/(linux|windows)/*ncnn* lite.ai.toolkit/lib
      cp you-path-to-downloaded-or-built-TNN/lib/(linux|windows)/*TNN* lite.ai.toolkit/lib

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 !!! : πŸš€ 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 ~ πŸ™ƒπŸ€ͺπŸ€. 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.

πŸ”‘οΈ How to link Lite.Ai.ToolKit? * 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.
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 .
β”œβ”€β”€ bin
β”œβ”€β”€ include
β”‚   β”œβ”€β”€ lite
β”‚   β”‚   β”œβ”€β”€ backend.h
β”‚   β”‚   β”œβ”€β”€ config.h
β”‚   β”‚   └── lite.h
β”‚   └── 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.

6. Model Zoo.

Lite.Ai.ToolKit contains 80+ 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.

Namepace Details
lite::cv::detection Object Detection. one-stage and anchor-free detectors, YoloV5, YoloV4, SSD, etc. βœ…
lite::cv::classification Image Classification. DensNet, ShuffleNet, ResNet, IBNNet, GhostNet, etc. βœ…
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 (πŸ”₯πŸ”₯πŸ’₯↑) 188Mb
lite::cv::detection::YoloV5 yolov5m.onnx yolov5 (πŸ”₯πŸ”₯πŸ’₯↑) 85Mb
lite::cv::detection::YoloV5 yolov5s.onnx yolov5 (πŸ”₯πŸ”₯πŸ’₯↑) 29Mb
lite::cv::detection::YoloV5 yolov5x.onnx yolov5 (πŸ”₯πŸ”₯πŸ’₯↑) 351Mb
lite::cv::detection::YoloX yolox_x.onnx YOLOX (πŸ”₯πŸ”₯!!↑) 378Mb
lite::cv::detection::YoloX yolox_l.onnx YOLOX (πŸ”₯πŸ”₯!!↑) 207Mb
lite::cv::detection::YoloX yolox_m.onnx YOLOX (πŸ”₯πŸ”₯!!↑) 97Mb
lite::cv::detection::YoloX yolox_s.onnx YOLOX (πŸ”₯πŸ”₯!!↑) 34Mb
lite::cv::detection::YoloX yolox_tiny.onnx YOLOX (πŸ”₯πŸ”₯!!↑) 19Mb
lite::cv::detection::YoloX yolox_nano.onnx YOLOX (πŸ”₯πŸ”₯!!↑) 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 !
πŸ”‘οΈ 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/

7. 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 πŸ”₯πŸ”₯ ! 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!

Example1: Video Matting using RobustVideoMatting2021πŸ”₯πŸ”₯πŸ”₯. 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:


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

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!

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);
  
  std::cout << "Default Version Done! Detected Face Num: " << detected_boxes.size() << std::endl;
  
  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::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!!

Example6: 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 (human segmentation, instance 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";

  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 (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

8. License.

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

9. References.

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

Expand for More References.

10. 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);

11. Contribute

How to add your own models and become a contributor? For specific steps, please refer to CONTRIBUTING.zh.md, or if you like this project please ❀️ consider ⭐️🌟 star this repo, as it is the simplest way to support me.

About

πŸ›  A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, YOLOv5, YOLOR, NanoDet, YOLOX, SCRFD, YOLOX . MNN, NCNN, TNN, ONNXRuntime, CPU/GPU.

License:GNU General Public License v3.0


Languages

Language:C++ 94.1%Language:C 4.6%Language:Objective-C 1.2%Language:CMake 0.2%Language:Python 0.0%Language:Shell 0.0%