Guided tour

1. 💡01

   GAN and VAE Networks on MNIST

   This project simulates Generative Adversarial Networks (GAN) and Variational Autoencoders (VAE) applied to the MNIST dataset. It aims to demonstrate the capabilities of these models in generating and reconstructing handwritten digits.

   • ✓Simulates GAN and VAE networks
2. 🛠02

   Monolithic Architecture Overview

   The architecture is component-based, with separate directories for GAN and VAE implementations. Each component contains Python files for training and utility functions.

   • !Component-based architecture
3. 📄03

   GAN Training Script

   The GAN/Training.py file showcases the training process for the GAN model, illustrating the developer's focus on structured training routines.

   GAN/Training.py

   import numpy as np
   import tensorflow as tf
   from gan_utils import generator, discriminator
   
   # Training parameters
   num_epochs = 100
   batch_size = 64
   
   # Training loop
   for epoch in range(num_epochs):
       ...

4. ✓04

   Testing Framework

   There are no configured tests or CI workflows in this project, indicating a potential area for improvement in quality assurance.

   • !No CI configured
5. 🚀05

   Deployment Information

   There are no CI/CD workflows or deployment targets configured for this project, which may limit its production readiness.

   • !No deployment workflows
6. ▶06

   Try It Out

   You can clone the repository to explore the GAN and VAE implementations locally.

   git clone https://github.com/shashankcm95/GAN-and-VAE-networks-on-MNIST-dataset

graph TD;
    A[MNIST Dataset] --> B[GAN Implementation];
    A --> C[VAE Implementation];
    B --> D[Training];
    C --> D;