Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Jewel 346542255e | 2 years ago | |
---|---|---|
.. | ||
python | 2 years ago | |
CMakeLists.txt | 2 years ago | |
README.md | 2 years ago | |
main.cpp | 2 years ago | |
picodet.cpp | 2 years ago | |
picodet.h | 2 years ago |
This project provides PicoDet image inference, webcam inference and benchmark using
Tencent's NCNN framework.
Download and Install Visual Studio from https://visualstudio.microsoft.com/vs/community/
Download and install OpenCV from https://github.com/opencv/opencv/releases
Download and install Vulkan SDK from https://vulkan.lunarg.com/sdk/home
Clone NCNN repository
git clone --recursive https://github.com/Tencent/ncnn.git
Build NCNN following this tutorial: Build for Windows x64 using VS2017
Add ncnn_DIR
= YOUR_NCNN_PATH/build/install/lib/cmake/ncnn
to system environment variables.
Build project: Open x64 Native Tools Command Prompt for VS 2019 or 2017
cd <this-folder>
mkdir -p build
cd build
cmake ..
msbuild picodet_demo.vcxproj /p:configuration=release /p:platform=x64
Build and install OpenCV from https://github.com/opencv/opencv
Download Vulkan SDK from https://vulkan.lunarg.com/sdk/home
Clone NCNN repository
git clone --recursive https://github.com/Tencent/ncnn.git
Build NCNN following this tutorial: Build for Linux / NVIDIA Jetson / Raspberry Pi
Set environment variables. Run:
export ncnn_DIR=YOUR_NCNN_PATH/build/install/lib/cmake/ncnn
Build project
cd <this-folder>
mkdir build
cd build
cmake ..
make
Download PicoDet ncnn model.
picodet_demo 0 0
picodet_demo 1 IMAGE_FOLDER/*.jpg
picodet_demo 2 VIDEO_PATH
picodet_demo 3 0
result: picodet min = 17.74 max = 22.71 avg = 18.16
Notice:
If benchmark speed is slow, try to limit omp thread num.
Linux:
export OMP_THREAD_LIMIT=4
PaddleDetection
Python Jupyter Notebook Markdown C++ Java other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》