Skip to content

README.md

Latest commit

 

History

History
78 lines (55 loc) · 2.42 KB

README.md

File metadata and controls

78 lines (55 loc) · 2.42 KB
Raw

🧠 Image Classification Using CNN

A Gradio-powered deep learning web app that classifies images as Dog, Cat, or Person using Convolutional Neural Networks.
Built with ❤️ using Python, PyTorch, OpenCV, and Gradio. Hosted on Hugging Face Spaces.

License: Apache 2.0 GitHub stars

📌 Table of Contents

📖 About the Project

This is an Image Classification Web Application built using Convolutional Neural Networks (CNN) to identify whether an image is of a Dog, Cat, or a Person.

  • The model was trained on a custom dataset curated by combining two Kaggle datasets:
    • Dogs vs. Cats
    • Man vs. Woman
  • Each class (Dog, Cat, Person) was created using 50 training and 50 testing images, giving a balanced dataset.
  • The model achieved a training accuracy of 99.63%.
  • The application features a sleek Gradio interface, and is hosted on Hugging Face Spaces for real-time predictions and demonstrations.

🧰 Tech Stack

  • Languages & Libraries:
    • Python
    • PyTorch
    • Scikit-learn
    • PIL (Python Imaging Library)
    • NumPy
    • OpenCV
    • Gradio (for UI)

🚀 Getting Started

To run this project locally on your system, follow these steps:

1. Clone the Repository

git clone https://github.com/shashibhushan01/image-classification-cnn.git
cd image-classification-cnn

### 2. Install Required Dependencies
Make sure Python 3.x is installed. Then run:- **pip install -r requirements.txt**

## 💻 Usage

--> Open the Gradio interface in your browser.

--> Upload an image of a dog, cat, or a person.

--> The CNN model will classify and display the result with confidence scores