Jetson-inference environment setup

1. Pre-use instructions

This tutorial is suitable for building a JETSON NANO image by yourself. If you directly use the YAHBOOM version of the image, you can ignore the tutorial.

2. The environment version configuration of this tutorial is shown in the figure:

If you don't want to build it completely by yourself, you can use the jetson-inference compression package we provide, transfer the compression package to JETSON NANO, decompress it, and start directly from "Install Module"

3. Start building

3.1 Download the required dependencies

xxxxxxxxxx
sudo apt-get update
sudo apt-get install git cmake

3.2 Download the relevant source code

xxxxxxxxxx
git clone https://github.com/dusty-nv/jetson-inference
cd jetson-inference
git submodule update --init ##If a network error is reported in the middle, you need to access the Internet scientifically and run it several times, otherwise the download will be incomplete

3.3 Download related python modules

Find the torch-1.8.0-cp36-cp36m-linux_aarch64.whl file from the attachments of our environment and transfer it to jetson nano

xxxxxxxxxx
sudo apt-get install libpython3-dev python3-numpy
sudo apt-get install python3-scipy
sudo apt-get install python3-pandas
sudo apt-get install python3-matplotlib
sudo apt-get install python3-sklearn
pip3 install torch-1.8.0-cp36-cp36m-linux_aarch64.whl

3.4 Modify the file

Edit jetson-inference/CMakePrebuild.sh. Comment out ./download-models.sh (add a # comment in front) as shown in the figure)

4. Install the model

Method 1: You can perform the following steps

xxxxxxxxxx
cd jetson-inference/tools
./download-models.sh

After making the selection, the model will be automatically downloaded to the file path of data/network. You need to access the Internet to download it normally

Method 2: You can find the package required by jetson-inference in the attachment provided by us for environment construction, transfer the compressed package in it to jetson-inference/data/network of jetso nano, and then decompress it Decompression command

xxxxxxxxxx
for tar in *.tar.gz; do tar xvf $tar; done

Note:

1. For decompressing multiple .gz files, use this command: for gz in *.gz; do gunzip $gz; done
2. To decompress multiple .tar.gz files, use the following command: for tar in *.tar.gz; do tar xvf $tar; done

5. Start compiling

xxxxxxxxxx
cd jetson-inference
mkdir build #Use the package we provide, this sentence can be omitted
cd build
cmake ../
make (or make -j4) #（in the build directory）
sudo make install #（in the build directory）

If an error is reported during the process, it means that the source code is not fully downloaded. Please return to step 3.2 and execute the git submodule update --init command, or download it from the browser. The method can be found on Baidu

6. Verify whether the installation is successful

 Install TensorFlow (optional)
Hello AI World