This is a digit generation project that employs Generative Adversarial Networks (GANs) to generate realistic handwritten digits.
GAN to generate digits in MNIST dataset
Generated digits (Similar to the ones in the MNIST dataset) using Wasserstein GANs.
A machine learning project that repurposes Bernoulli Naive Bayes as a generative model to synthesize handwritten digits from the MNIST dataset. Implements pixel-wise probability learning, sampling, and image generation with smoothing techniques.
This repository is made as supplementary material for a tutorial. The tutorial shows how to use Recurrent Neural Nets as generative models.
Conditional GAN for generating handwritten digits with class control. TensorFlow implementation with DCGAN architecture and training visualization.
Add a description, image, and links to the digit-generation topic page so that developers can more easily learn about it.
To associate your repository with the digit-generation topic, visit your repo's landing page and select "manage topics."