NanoDet NCNN Demo

This project provides NanoDet image inference, webcam inference and benchmark using Tencent's NCNN framework.

How to build

Windows

Step1.

Download and Install Visual Studio from https://visualstudio.microsoft.com/vs/community/

Step2.

Download and install OpenCV from https://github.com/opencv/opencv/releases

Step3(Optional).

Download and install Vulkan SDK from https://vulkan.lunarg.com/sdk/home

Step4.

Clone NCNN repository

git clone --recursive https://github.com/Tencent/ncnn.git

Build NCNN following this tutorial: Build for Windows x64 using VS2017

Step5.

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 nanodet_demo.vcxproj /p:configuration=release /p:platform=x64

Linux

Step1.

Build and install OpenCV from https://github.com/opencv/opencv

Step2(Optional).

Download Vulkan SDK from https://vulkan.lunarg.com/sdk/home

Step3.

Clone NCNN repository

git clone --recursive https://github.com/Tencent/ncnn.git

Build NCNN following this tutorial: Build for Linux / NVIDIA Jetson / Raspberry Pi

Step4.

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

Run demo

Download NanoDet ncnn model.

• NanoDet ncnn model download link

Copy nanodet_m.param and nanodet_m.bin to demo program folder.

Webcam

nanodet_demo 0 0

Inference images

nanodet_demo 1 IMAGE_FOLDER/*.jpg

Inference video

nanodet_demo 2 VIDEO_PATH

Benchmark

nanodet_demo 3 0

---

Notice:

If benchmark speed is slow, try to limit omp thread num.

Linux:

export OMP_THREAD_LIMIT=4