Jetson reference environment construction

1.Instructions before use

This tutorial is suitable for independently building images of Jetson orin nano. Directly using the YAHBOOM version of the image can be ignored for the tutorial.

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

If you don't want to build it completely on your own, you can use the Jetson reference compressed package we provided, pass the compressed package into Jetson orin nano, decompress it, and start looking at the "installation module" directly

3.Start building

3.1 Dependencies required for download


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

3.2 Download relevant source code


xxxxxxxxxx
git clone https://github.com/dusty-nv/jetson-inference
cd jetson-inference
git submodule update --init

3.3 Download relevant Python modules

Find torch-1.8.0-cp36-cp36m-Linux from the attachment we built in our environment_ Aarch64.whl Transfer this file to Jetson orin 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 Modifying Files

Edit Jetson reference/CMakePrebuild.sh. Put/ Download models. sh comment out (with a # comment added 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 a selection, the model will be automatically downloaded to the file path of data/network, and scientific internet access is required to download it normally

Method 2: You can find the package required for Jetson reference in the attachment we provided for environment setup, transfer the compressed package to Jetso orin nano's Jetson reference/data/network, and then decompress itDecompression command


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

notes:

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

5.Start Compilation


xxxxxxxxxx
cd jetson-inference    
mkdir build  
cd build
cmake ../
make (或者make -j4)    #（build）
sudo make install      #（build）

If an error is reported midway, it indicates that the source code download is incomplete. Please go back to step 3.2 and execute the command git submiodule update - init again, or download from a browser using Baidu

6.Verify if the installation was successful


x
cd jetson-inference/build/aarch64/bin

./imagenet-console ./images/bird_0.jpg output.jpg

Find the corresponding directory and view output.jpg as follows. The recognition results will be displayed at the top of the image.

appendix