Skip to content

ryley-o/I_cVAEGAN

Repository files navigation

I. by ryley-o.eth

A model on the blockchain

This repository documents the source code and training process for aConditional Variational Autoencoder Generative Adversarial Network Hybrid(cVAE-GAN) model used for the generative art project, I. by ryley-o.eth.

A small, efficient conditional cVAE-GAN implementation for 64x64 images using TensorFlow/Keras. This implementation is designed to be easily quantizable and deployable to blockchain via TensorFlow.js.

Note: LLM agent-based coding was used heavily when creating the code for this model. AI was embraced for reasons closely related to why this model was created.

Features

  • Conditional Variational Autoencoder (cVAE)
  • Generative Adversarial Network (GAN)
  • Conditional consistency and contrastive regularization
  • Training schedule to blend cVAE's and GAN's strengths while focusing in interpolation stability
  • Hyper-compact model
  • Quantizable
  • Deployable to blockchain

Usage

You can create the model that was uploaded to the blockchain by running the following commands:

# Train the model
python3 train_vaegan3_revb.py

# Export TFJS quantized model
python3 export_vaegan3_revb_tfjs.py

# Run python server
python3 -m http.server 8000

# Run the model in the browser, refresh for new images
open http://localhost:8000/simple_vaegan3_interp.html

# if you want to generate a grid of output images, run the following command
python3 generate_grid_vaegan3.py

About

The code used to build, train and export the cVAE-GAN used by the generative art project I. by ryley-o.eth

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors