rsa-project

Table of Contents

• Setup Jetson Nano
  • Export Paths for CUDA
  • Build OpenCV with GStreamer support
  • Create pip package for Compiled OpenCV
  • Clone ultralytics
  • Setup Python 3.8
  • Install PyTorch 0.11.0 and TorchVision 0.12.0
  • Install ultralytics
• Setup Project
  • Clone this repository
  • Run Stream Server
  • Run Object Detection App

Setup Jetson Nano JetPack 4.6 (L4T R32.6.1)

Export Paths for CUDA

Add the following lines to ~/.bashrc

export PATH=/usr/local/cuda-10.2/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda-10.2/lib64:$LD_LIBRARY_PATH
export FORCE_CUDA="1"

Build OpenCV with GStreamer support

Follow this guide (Build might take a couple of hours)

Create pip package for Compiled OpenCV

Create a dummy package for OpenCV installed from source (to prevent pip from trying to install another version of OpenCV)

cd ~
mkdir opencv-pip
cd opencv-pip

touch setup.py

Add the following content to setup.py

from setuptools import setup

setup(
		name='opencv-python',
		version='4.10.0-pre',
		description='Dummy package for OpenCV installed from source',
		install_requires=[],
)

Install dummy package

pip install --no-deps opencv-python

Clone ultralytics

git clone https://github.com/ultralytics/ultralytics
cd ultralytics

Setup Python 3.8

Jetson Nano comes with Python 3.6.9, but we need Python 3.8.

sudo apt-get update
sudo apt install -y python3.8 python3.8-venv python3.8-dev python3-pip libopenmpi-dev libomp-dev libopenblas-dev libblas-dev libeigen3-dev libcublas-dev
python3.8 -m venv venv --system-site-packages
source venv/bin/activate

Install PyTorch 0.11.0 and TorchVision 0.12.0

Versions that work with CUDA 10.2

$ pip install -U pip wheel gdown
$ gdown https://drive.google.com/uc?id=1hs9HM0XJ2LPFghcn7ZMOs5qu5HexPXwM
$ gdown https://drive.google.com/uc?id=1m0d8ruUY8RvCP9eVjZw4Nc8LAwM8yuGV
$ python3.8 -m pip install torch-*.whl torchvision-*.whl

Install ultralytics

pip install .

Setup Project

Make sure you are inside the virtual environment created in the previous steps

Clone this repository

git clone https://github.com/digas99/rsa-project
cd rsa-project
pip install -r requirements.txt

Run Stream Server

python3 src/stream.py

Run Object Detection App

python3 src/app.py

Architecture Diagram