Brainy Pi

Available to select audience (currently beta)

BrainyPi

Pytorch examples

Description

Pytorch has been popular for its performance and easy to implementation techniques. Lets explore different pytorch applications on brainyPi.

INFO
This documentation is for Rbian OS version: 0.7.2-beta & for Pytorch version 1.13.1.
To check the version of Rbian run the command in terminal
				
					os-version
Note: If the command fails or gives error then Rbian version is < 0.7.2-beta.
To check the version of Pytorch run the command in python
				
					import torch as tr
print(tr.__version__)

People Counter

  • People Counter counts the number of people in the image and prints it on the terminal. We can count people from videos, images, camera stream etc.
  • Prerequisites
				
					pip3 install numpy==1.24.1
pip3 install pillow
  • Clone the repository
				
					git clone https://github.com/brainypi/BrainyPi-AI-Examples.git
cd BrainyPi-AI-Examples/Pytorch/people-counter
  • Run Image segmentation example
				
					python people_counter.py mb1-ssd models/mobilenet-v1-ssd-mp-0_675.pth models/voc-model-labels.txt video.mp4
  • Input
    • Parameter1: Model name
    • Parameter2: Model path
    • Parameter3: Labels file path
    • Parameter4: Input Video: In case this parameter is not provided, it will take the input from camera directly.
  • Output
    • Shows the Label with probability on terminal and the detected objects image.

Vehicle Counter

  • We will be implementing Vehicle Counter application on BrainyPi which is trained on coco dataset including car, bus, bicycle, motorbike vehicle.
  • Prerequisites
				
					pip3 install numpy==1.24.1
  • Clone the repository
				
					git clone https://github.com/brainypi/BrainyPi-AI-Examples.git
cd BrainyPi-AI-Examples/Pytorch/vehicle-counter
  • Run Image segmentation example
				
					python vehicle_counter.py mb1-ssd models/mobilenet-v1-ssd-mp-0_675.pth models/voc-model-labels.txt video.mp4
  • Input
    • Parameter1: Model name
    • Parameter2: Model path
    • Parameter3: Labels file path
    • Parameter4: Input Video : In case this parameter is not provided, it will take the input from camera directly.
  • Output
    • Shows the Label with probability on terminal and the detected objects image.

Previous

<< GPIO Examples

Next

Opencv Examples >>

Index