---
title: "FastAPI Image Classification with VGG16"
emoji: "🔍"
colorFrom: "indigo"
colorTo: "purple"
sdk: "docker"
python_version: "3.9"
sdk_version: "1.0"
suggested_hardware: "cpu-upgrade"
suggested_storage: "medium"
app_file: "your_script_name.py"
app_port: 8000
base_path: "/"
fullWidth: true
header: "default"
short_description: "Classify images using VGG16 in FastAPI."
tags: ["image-classification", "VGG16", "FastAPI", "Docker", "deep-learning"]
thumbnail: "http://example.com/path_to_custom_thumbnail.jpg"
pinned: false
hf_oauth: false
disable_embedding: false
startup_duration_timeout: "30m"
custom_headers:
  cross-origin-embedder-policy: "require-corp"
  cross-origin-opener-policy: "same-origin"
  cross-origin-resource-policy: "cross-origin"
license: "mit"
---

# FastAPI Image Classification with VGG16

## Description

This Space uses a FastAPI application to classify images via a pre-trained VGG16 model. The application is containerized using Docker for easy deployment and scalability. Users can upload an image, and the model will classify it into one of two categories.

## How to Use

1. **Start the Docker Container:**
   - Build the Docker image and run it using:
     ```bash
     docker build -t image-classification .
     docker run -p 8000:8000 image-classification
     ```
   
2. **Accessing the API:**
   - Open your browser and go to `http://localhost:8000/docs`.
   - Use the `/predict/` endpoint to submit an image file and receive the classification result.

## Requirements

- Docker
- Python 3.9

## Installation

1. Clone the repository:
   ```bash
   git clone <repository-url>
   cd <repository-directory>