ImageVisionAPI

Image Classification Web Application with FastAPI and Gradio

This project demonstrates a complete pipeline for a image classification system using Convolutional Neural Networks (CNNs), FastAPI, Gradio, and Docker. The project includes user authentication, image upload, classification, and history retrieval, with a focus on continuous integration and deployment.

Table of Contents

• Introduction
• Features
• Technologies
• Setup
• Usage
• API Documentation
• CI/CD
• License

Introduction

This project provides a comprehensive example of how to build a machine learning application with a REST API for model inference and a user-friendly interface for interacting with the model. It includes user authentication, image upload functionality, and a history of past classifications.

Features

• CNN Model: Image classification using a Convolutional Neural Network built with PyTorch.
• FastAPI: High-performance API backend.
• Gradio: User-friendly interface for image upload and classification. (TODO)
• PostgreSQL: Relational database for storing user data and classification history.
• User Authentication: Secure JWT-based authentication.
• CI/CD: Continuous integration and deployment using GitHub Actions.
• Docker: Containerized deployment for easy setup and scaling.

Technologies

• Python
• PyTorch
• FastAPI
• Gradio
• SQLAlchemy
• PostgreSQL
• JWT
• Docker
• GitHub Actions
• Poetry

Setup

Prerequisites

• Docker
• Docker Compose
• Poetry
• Python 3.10+

Clone the repository

git clone https://github.com/username/repository.git
cd repository

Install dependencies

poetry install

Setup environment variables

Create a .env file in the root directory. See env_example.txt for more details.

Run the application

docker-compose up --build

The FastAPI application will be available at http://localhost:8000.

Usage

FastAPI Endpoints

• Register: POST /api/v1/auth/register
• Login: POST /api/v1/auth/login
• Logout: POST /api/v1/auth/logout
• Classify Image: POST /api/v1/ml/predict
• Get User Info: GET /api/v1/users/me
• Get History: GET /api/v1/users/me/history

API Documentation

FastAPI provides interactive API documentation (Swagger) at http://localhost:8000/docs and http://localhost:8000/redoc.

CI/CD

The project includes a GitHub Actions workflow for continuous integration and deployment and defined in .github/workflows.

License

This project is licensed under the MIT License. See the LICENSE file for more information.