jigsaw-vit-clothing1m-obsa4930

Clothing1M Image Classifier

This project is a deep learning-based image classifier for the Clothing1M dataset. It uses a Vision Transformer (ViT) model to classify clothing images into one of 14 categories. The application is built with PyTorch and Gradio for an interactive web interface.

---

Features

• Model Architecture: Vision Transformer (ViT) with a custom classification head.
• Interactive Interface: Built with Gradio for easy image classification.
• Pretrained Model: Downloads the pretrained model from the Hugging Face Hub.
• Example Images: Includes example images for testing the classifier.

---

Installation

Prerequisites

• Python 3.8 or higher
• pip package manager

Steps

1. Clone the repository:

   git clone https://github.com/your-username/clothing1m-classifier.git
   cd clothing1m-classifier
   
   

2. Install the required dependencies:

pip install -r requirements.txt

Usage

1. Run the application:

python app.py

1. Open the Gradio interface in your browser (default: http://127.0.0.1:7860).

2. Upload an image or select an example image to classify it into one of the 14 clothing categories.

Project Structure

clothing_classifier/ ├── app.py # Main application script ├── model_jigsaw_nested.py # Model architecture ├── utils.py # Utility functions ├── requirements.txt # Required dependencies ├── examples/ # Example images │ ├── example1.jpg │ ├── example2.jpg │ └── example3.jpg

Model Details

Architecture: Vision Transformer (ViT) with a custom classification head. Pretrained Model: The model is downloaded from the Hugging Face Hub: Repository: Obsaa/jigsaw-vit-clothing1m-obsa4930 File: model.pth

Dependencies

The project requires the following Python libraries:

torch torchvision einops timm numpy gradio pillow huggingface_hub

Example Categories

The model classifies images into the following 14 clothing categories:

T-Shirt Shirt Knitwear Chiffon Sweater Hoodie Windbreaker Jacket Down Coat Suit Blazer Vest Sweatpants Jeans

Acknowledgments

JigsawViT Clothing1M Dataset Hugging Face Hub Gradio

Summary

This README.md file provides an overview of the project, including installation instructions, usage, project structure, and dependencies. You can customize it further based on your specific requirements. Let me know if you need additional changes!

Summary