Sheep or Goat?

A machine learning image classifier that looks at an image and guesses if it's a sheep or a goat.
Demo Website »

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
   • Development
   • Deployment
3. License
4. Contact
5. Acknowledgements

About The Project

Upload an image of a real life sheep or goat and the trained neural network will try to determine if it is a sheep or a goat. The model was trained with images from Google Images as well as some databases from Kaggle.

Built With

• Fast.ai
• Paperspace
• Render

Getting Started

Here is a guide if you want to clone my website and modify it for yourself, all the way to deployment.

Prerequisites

• git

Installation

1. Clone the repo

   git clone https://github.com/AjayLiu/sheep-or-goat.git

2. Create and train your model as outlined in https://youtu.be/XfoYk_Z5AkI
3. Upload your model (.pkl) in path/models

Development

To run the website, use something like the VSCode Code Runner Extension to run app.py. Then you can view the site using the URL provided from the command line output.

Deployment

1. Publish the site on Render using continuous git integration.
2. Add environment variable PYTHON_VERSION=3.9.15

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Ajay Liu - contact@ajayliu.com

Project Link: https://github.com/AjayLiu/sheep-or-goat

Acknowledgements

• Repo that the website is based off of