Project 2c - Jetson Nano setup, for Machine Learning

Project start: 19 December 2021

Project finish: 19 December 2021

Last updated: 13 August 2022

Objective: setup of Jetson Nano for computer vision and machine learning

Add these environment variables to the .bashrc file which is a hidden file located in your $HOME directory:

export OPENBLAS_CORETYPE=ARMV8

export LD_PRELOAD=/usr/lib/aarch64-linus-gnu/libgomp.so.1

activate virtual environment:

cd $HOME

cd Public/Projects

source myPython36VEnv/bin/activate

install some Python modules:

pip3 install -U setuptools==49.6.0 wheel numpy==1.16.1 future==0.17.1 mock==3.0.5 testresources

install OpenCV:

pip3 install -U opencv-python

install TensorFlow:

pip3 install -U  h5py==2.9.0

pip3 install -U keras-preprocessing==1.0.5

pip3 install --pre --extra-index-url https://developer-download.nvdia.com/compute/redist/jp/v45 tensorflow<2

update TensorFlow:

pip3 install --pre --extra-index-url https://developer-download.nvdia.com/compute/redist/jp/v45 tensorflow==2.5.0+nv21.6

install even more Python modules:

pip3 install -U scipy sklearn matplotlib

check that all modules have been installed:

pip3 list --local
->

Package     Version
-------------  ---------------
h5py		2.10.0
...
matplotlib	3.3.4
...
numpy		1.19.5
...
opencv-python	4.5.4.60
...
scikit-learn	0.24.2
...
scipy		1.5.4
...
sklearn		0.0
...
tensorflow	2.5.0+nv21.6

If you have any questions or need clarification please contact me: jscanova@gmail.com