This repo is a DNN framework for Boosting DNN Cold Inference. This repo is based on ncnn.

The following instructions are executed on a PC with an operating system of Ubuntu 22.04.

1. Install NDK and adb.

   $ mkdir ./NDK && cd ./NDK
   $ wget https://dl.google.com/android/repository/android-ndk-r21e-linux-x86_64.zip
   $ unzip ./android-ndk-r21e-linux-x86_64.zip
   $ echo export ANDROID_NDK=$HOME/NDK/android-ndk-r21e >> ~/.bashrc
   $ source ~/.bashrc
   $ sudo apt install adb

2. Connect PC and android phone via USB cable.

3. Clone this repo.

   $ git clone --recursive https://github.com/Yeeethan00/NNV12.git 
   $ cd ./NNV12

4. Build and push models to android phone.

   $ cd ./scripts
   $ chmod +x ./init_arm64.sh
   $ ./init_arm64.sh

5. Deploy models.

   $ chmod +x ./deployed_arm64.sh
   $ ./deployed_arm64.sh

6. Run NNV12.

   $ chmod +x ./run_arm64.sh
   $ ./run_arm64.sh

7. The result of latency is shown in "./scripts/output.csv".

There are results get from Meizu 16T (Snapdragon 855).

The following instructions are executed on a Jetson Nano.

1. Install Vulkan and CMake.

   $ cd ./scripts
   $ chmod +x ./install_jetson.sh
   $ ./install_jetson.sh

2. Clone this repo.

   $ git clone --recursive https://github.com/Yeeethan00/NNV12.git 
   $ cd ./NNV12

3. Build project.

   $ chmod +x ./init_jetson.sh
   $ ./init_jetson.sh

4. Deploy models.

   $ chmod +x ./deployed_jetson.sh
   $ ./deployed_jetson.sh

5. Run NNV12.

   $ chmod +x ./run_jetson.sh
   $ ./run_jetson.sh

6. The result of latency is shown in "./scripts/output.csv".

There are results get from Jetson Nano.