Skip to content

Python Flask and Streamlit web app that uses a ResNet50 PyTorch model to classify 15 animal categories with high accuracy. Upload images and get instant, real-time predictions via a clean, user-friendly interface.

License

Notifications You must be signed in to change notification settings

ShauryaDusht/animal-classification-flask-app

Repository files navigation

🚀 Animal Classification Web App

Python Flask License PyTorch Streamlit

Transform your animal image classification experience with our powerful Flask web application! Upload and instantly classify animals using state-of-the-art machine learning.

Live Demo

The application is deployed and can be accessed at: https://animal-classification-flask-app-yay48qunbup3unge4g6fkx.streamlit.app

Key Features

🤖 Advanced Classification

  • 15 Animal Categories - Accurately identifies Bears, Birds, Cats, Cows, Deer, Dogs, Dolphins, Elephants, Giraffes, Horses, Kangaroos, Lions, Pandas, Tigers, and Zebras
  • High Accuracy - 99.47% test accuracy and 97.43% train accuracy
  • ResNet50 CNN - Powered by state-of-the-art deep learning architecture

💻 User-Friendly Interface

  • Simple Upload - Easy-to-use image upload functionality
  • Instant Results - Real-time classification processing
  • Clean Design - Intuitive web interface

🚀 Quick Start

Installation

  1. 🧑‍💻 Clone the Repository
git clone https://github.com/ShauryaDusht/animal-classification-flask-app
cd animal-classification-flask-app
  1. 🔧 Install Dependencies
pip install -r requirements.txt
  1. 📁 Project Structure
AnimalClassification/
│
├── static/
│   └── styles.css
├── templates/
│   └── index.html
│ 
├── animal_classifier.pkl
├── app.py
├── streamlit_app.py
└── requirements.txt

🚀 Start the Server

  1. Start flask server(for windows)
python app.py
  1. Open a web browser and go to http://127.0.0.1:5000/

🛠️ Technologies Used

⚡ Backend:

  • Flask for robust server-side operations
  • PyTorch for machine learning model deployment

🎯 Frontend:

  • Clean, responsive web interface
  • Simple upload and classification workflow

🖥️ Model:

  • ResNet50 CNN architecture
  • Trained on Animal Data dataset from Kaggle
  • High accuracy classification

📧 Contact

Feel free to reach out to me via email for any queries or collaboration opportunities:

📧 [email protected]

About

Python Flask and Streamlit web app that uses a ResNet50 PyTorch model to classify 15 animal categories with high accuracy. Upload images and get instant, real-time predictions via a clean, user-friendly interface.

Topics

Resources

License

Stars

Watchers

Forks

Languages