Baike.dev
All toolsOnline toolsAI codingTrendingOpen sourceNewsSubmit
Log in
< Back to tools
M

Msnhnet

> 编程语言
Open source

(yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.

739 stars0 likes2 views
WebsiteGitHub

About

(yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.

Msnhnet(V2.0 Focusing on Robot Vision)

English| 中文 |CSDN

A mini pytorch inference framework which inspired from darknet.

OS supported (you can check other OS by yourself)

windows linux mac Loongnix
checked
gpu

CPU checked

Intel i7 raspberry 3B raspberry 4B Jeston NX Loongson
checked

Features

  • C++ Only. 3rdparty blas lib is optional, also you can use OpenBlas.

  • OS supported: Windows, Linux(Ubuntu checked) and Mac os(unchecked).

  • CPU supported: Intel X86, AMD(unchecked) and ARM(checked: armv7 armv8 arrch64).

  • x86 avx2 supported.(Working....)

  • arm neon supported.(Working....)

  • A cv lib like opencv is supported for msnhnet.(MsnhCV)

  • conv2d 3x3s1 3x3s2 winograd3x3s1 is supported(Arm)

  • Keras to Msnhnet is supported. (Keras 2 and tensorflow 1.x)

  • GPU cuda supported.(Checked GTX1080Ti, Jetson NX)

  • GPU cudnn supported.(Checked GTX1080Ti, Jetson NX)

  • GPU fp16 mode supported.(Checked GTX1080Ti, Jetson NX.)

  • ps. Please check your card wheather fp16 full speed is supported.

  • c_api supported.

  • keras 2 msnhnet supported.(Keras 2 and tensorflow 1.x, part of op)

  • pytorch 2 msnhnet supported.(Part of op, working on it)

  • MsnhnetSharp supported.

  • A viewer for msnhnet is supported.(netron like)

  • Working on it...(Weekend Only (╮（╯＿╰）╭))

Tested networks

  • lenet5
  • lenet5_bn
  • alexnet(torchvision)
  • vgg16(torchvision)
  • vgg16_bn(torchvision)
  • resnet18(torchvision)
  • resnet34(torchvision)
  • resnet50(torchvision)
  • resnet101(torchvision)
  • resnet152(torchvision)
  • darknet53(Pytorch_Darknet53)
  • googLenet(torchvision)
  • mobilenetv2(torchvision)
  • yolov3(u版yolov3)
  • yolov3_spp(u版yolov3)
  • yolov3_tiny(u版yolov3)
  • yolov4(u版yolov3)
  • fcns(pytorch-FCN-easiest-demo)
  • unet(bbuf keras)
  • deeplabv3(torchvision)
  • yolov5s(U版yolov5, for params)

  • yolov5m(U版yolov5,for params)

  • mobilenetv2_yolov3_lite (cudnn does not work with GTX10** Pascal Card, please use GPU model only)
  • mobilenetv2_yolov3_nano (cudnn does not work with GTX10** Pascal Card, please use GPU model only)
  • yoloface100k (cudnn does not work with GTX10** Pascal Card, please use GPU model only)
  • yoloface500k (cudnn does not work with GTX10** Pascal Card, please use GPU model only)

  • Thanks: https://github.com/dog-qiuqiu/MobileNetv2-YOLOV3

  • pretrained models. 链接：https://pan.baidu.com/s/1mBaJvGx7tp2ZsLKzT5ifOg 提取码：x53z
  • pretrained models. Link : Google Drive
  • Examples here.

Yolo Test

  • Win10 MSVC 2017 I7-10700F

    net yolov3 yolov3_tiny yolov4
    time 380ms 50ms 432ms

  • ARM(Yolov3Tiny cpu)

    cpu raspberry 3B raspberry 4B Jeston NX
    with neon asm ? 0.432s ?

Yolo GPU Test

  • Ubuntu16.04 GCC Cuda10.1 GTX1080Ti

    net yolov3 yolov3_tiny yolov4
    time 30ms 8ms 30ms

  • Jetson NX

    net yolov3 yolov3_tiny yolov4
    time 200ms 20ms 210ms

Yolo GPU cuDnn FP16 Test

  • Jetson NX
    net yolov3 yolov4
    time 115ms 120ms

Yolov5s GPU Test

  • Ubuntu18.04 GCC Cuda10.1 GTX2080Ti
    net yolov5s yolov5s_fp16
    time 9.57ms 8.57ms

Mobilenet Yolo GPU cuDnn Test

  • Jetson NX
    net yoloface100k yoloface500k mobilenetv2_yolov3_nano mobilenetv2_yolov3_lite
    time 7ms 20ms 20ms 30ms

DeepLabv3 GPU Test

  • Ubuntu18.04 GCC Cuda10.1 GTX2080Ti
    net deeplabv3_resnet101 deeplabv3_resnet50
    time 22.51ms 16.46ms

Requirements

  • OpenCV4 (optional) https://github.com/opencv/opencv
  • Qt5 (optional. for Msnhnet viewer) http://download.qt.io/archive/qt/
  • opengl(optional. for MsnhCV GUI) .
  • glew(optional. for MsnhCV GUI) http://glew.sourceforge.net/ .
  • glfw3(optional. for MsnhCV GUI) https://www.glfw.org/.
  • cuda10+ cudnn 7.0+.(optional. for GPU)

Video tutorials(bilibili)

  • Build on Linux
  • Build on Windows
  • Pytorch Params to msnhbin

How to build

  • With CMake 3.15+
  • Viewer can not build with GPU.
  • Options

ps. You can change omp threads by unchecking OMP_MAX_THREAD and modifying "num" val at CMakeLists.txt:52

  • Windows
  1. Compile opencv4 (optional)
  2. Config environment. Add "OpenCV_DIR" (optional)
  3. Get qt5 and install. http://download.qt.io/ (optional)
  4. Add qt5 bin path to environment (optional).
  5. Get glew for MsnhCV Gui.http://glew.sourceforge.net/ (optional).
  6. Get glfw3 for MsnhCV Gui.https://www.glfw.org/ (optional).
  7. Extract glew, add glew path to "CMAKE_PREFIX_PATH" (optional).
  8. Compile gflw3 with cmake, add gflw3 cmake dir to "GLFW_DIR" (optional).
  9. Then use cmake-gui tool and visual studio to make or use vcpkg.
  • Linux(Ubuntu)

ps. If you want to build with Jetson, please uncheck NNPACK, OPENBLAS, NEON.

bash

sudo apt-get install build-essential
sudo apt-get install qt5-default      #optional
sudo apt-get install libqt5svg5-dev   #optional
sudo apt-get install libopencv-dev    #optional
sudo apt-get install libgl1-mesa-dev libglfw3-dev libglfw3 libglew-dev #optional

#config 
sudo echo /usr/local/lib > /etc/ld.so.conf.d/usrlib.conf
sudo ldconfig

# build Msnhnet
git clone https://github.com/msnh2012/Msnhnet.git
mkdir build 

cd Msnhnet/build
cmake -DCMAKE_BUILD_TYPE=Release ..  
make -j4
sudo make install

vim ~/.bashrc # Last line add: export PATH=/usr/local/bin:$PATH
sudo ldconfig
  • MacOS(MacOS Catalina) Without viewer

PS: XCode should be pre-installed.

Please download cmake from official website with gui support and the source code of yaml and opencv.

…

Test Msnhnet

    1. Download pretrained model and extract. eg.D:/models.
    1. Open terminal and cd "Msnhnet install bin". eg. D:/Msnhnet/bin
    1. Test yolov3 "yolov3 D:/models".
    1. Test yolov3tiny_video "yolov3tiny_video D:/models".
    1. Test classify "classify D:/models".

View Msnhnet

    1. Open terminal and cd "Msnhnet install bin" eg. D:/Msnhnet/bin
    1. run "MsnhnetViewer"

PS. You can double click "ResBlock Res2Block AddBlock ConcatBlock" node to view more detail ResBlock

Res2Block

AddBlock

ConcatBlock

How to convert your own pytorch network

  • pytorch2msnhnet
  • ps:
  • 1 . Please check out OPs which supported by pytorch2msnhnet before trans.
  • 2 . Maybe some model can not be translated.
  • 3 . If your model contains preprocessors and postprocessors which are quite complicated, please trans backbone first and then add some OPs manually.
  • 4 . As for yolov3 & yolov4, just follow this video. You can find "pytorch2msnhbin" tool here.

About Train

  • Just use pytorch to train your model, and export as msnhbin.
  • eg. yolov3/v4 https://github.com/ultralytics/yolov3

Enjoy it! :D

Acknowledgement

Msnhnet got ideas and developed based on these projects：

  • DarkNet
  • NCNN
  • ACL

3rdparty Libs

  • stb_image
  • yaml-cpp
  • imGui
  • mpeg

加群交流

Issues· 0 open

View all issuesOpen on GitHub

No open issues yet, or sync has not completed.

> Tags

C++darknetinference-enginejetson-nxmobilenetv2

No comments yet. Be the first to share.

> Details

PublishedAug 1, 2026
UpdatedSep 17, 2026
Category编程语言
PricingOpen source

> Related tools

T
TypeScript
JavaScript 的超集，为前端与全栈提供静态类型
P
Python
通用编程语言，广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言