https://github.com/mjahmadee/vae

Variational Autoencoder
https://github.com/mjahmadee/vae

isomap latent-space pca vae variational-autoencoder

Last synced: about 1 year ago
JSON representation

Variational Autoencoder

• Host: GitHub
• URL: https://github.com/mjahmadee/vae
• Owner: MJAHMADEE
• License: mit
• Created: 2023-07-18T11:58:26.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-03-16T12:54:53.000Z (almost 2 years ago)
• Last Synced: 2025-01-11T08:51:39.578Z (about 1 year ago)
• Topics: isomap, latent-space, pca, vae, variational-autoencoder
• Language: Jupyter Notebook
• Homepage:
• Size: 13.6 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Variational Autoencoders for Image Classification 🤖👚

![Python](https://img.shields.io/badge/Python-3.x-blue.svg)

![TensorFlow](https://img.shields.io/badge/TensorFlow-2.x-orange.svg)

![Machine Learning](https://img.shields.io/badge/Machine%20Learning-VAE-green.svg)

This repository contains implementations of Variational Autoencoders (VAE) and their application in image classification tasks, primarily focusing on the Fashion MNIST dataset.

## Features 🌟

- Implements Variational Autoencoders (VAE) for generating and reconstructing images.

- Utilizes TensorFlow and Keras for building and training models.

- Supports dimensionality reduction for improving image classification using K-Nearest Neighbors (KNN).

- Includes detailed performance evaluation with confusion matrices and classification reports.

- Provides visualizations of training losses, latent spaces, and generated images.

## Setup and Installation 🛠️

1. Clone the repository.

2. Install the necessary dependencies using `pip install -r requirements.txt`.

3. Ensure TensorFlow with GPU support is installed if GPU processing is desired.

## Datasets 📁

The primary dataset used is Fashion MNIST, which includes 60,000 training images and 10,000 testing images of 10 fashion categories.

## Training the Model 🚀

- Execute the VAE training script to learn latent representations of images.

- The model automatically performs image reconstruction and generation.

## Image Classification 🧪

- Use the encoded representations from VAE as features for training a KNN classifier.

- Evaluate the classifier's performance using the test dataset and calculate various metrics like accuracy, precision, recall, and F1-score.

## Results and Evaluation 📊

- Check the output directory for training logs, model checkpoints, and generated images.

- Review the classification reports and confusion matrices to understand model performance.

## Contributing 🤝

Contributions, issues, and feature requests are welcome! Feel free to check the issues page.

## License 📜

This project is available under the MIT License. See the LICENSE file for more details.

## Acknowledgements 🙌

- TensorFlow and Keras documentation for providing extensive guides and API documentation.

- Fashion MNIST dataset creators for providing a benchmark dataset for image classification tasks.

For more details, please visit the [GitHub repository](https://github.com/MJAHMADEE/VAE/).