https://github.com/mehassanhmood/computervision

Image generation using Variation Autoencoders and Genrative adversarial Networks.
https://github.com/mehassanhmood/computervision

computer-vision deep-learning gans genrative-ai vae

Last synced: 3 months ago
JSON representation

Image generation using Variation Autoencoders and Genrative adversarial Networks.

• Host: GitHub
• URL: https://github.com/mehassanhmood/computervision
• Owner: mehassanhmood
• Created: 2024-03-19T17:31:30.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-07T08:10:43.000Z (about 1 year ago)
• Last Synced: 2025-02-01T10:11:43.443Z (4 months ago)
• Topics: computer-vision, deep-learning, gans, genrative-ai, vae
• Language: Jupyter Notebook
• Homepage:
• Size: 19.1 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Digging deep into VAEs And GANs

## Introduction: 

Generative models play a vital role in various applications, including image generation, data augmentation, and anomaly detection. Two popular generative models are Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). In this project, i compared GANs and VAEs built from scratch using the Celeb-A dataset, a widely used benchmark dataset for facial image generation.

## Training and Evaluation: 

1. GANs:    

  Training GANs can be challenging due to instability and mode collapse issues. However, when properly trained, GANs can generate high-quality and diverse images. Evaluation metrics for GANs include Inception Score (IS) and Fréchet Inception Distance (FID), which measure the quality and diversity of generated images.    

![Tensor Board](tensorboard.jpg)

3. VAEs:    

  VAEs are more stable during training compared to GANs but may produce less realistic images. Evaluation metrics for VAEs include reconstruction loss and the quality of generated images in the latent space.

   ![Total and Reconstruction Loss](tl_rl.png)

   ![Kulbach Liebler Loss](kl_loss.png)

## Scope of project

-  The focus of this project leaned towards theoretical aspects. Hence focus was on the implementation of the concepts and not the results generated.