A Tensorflow implementation of a Variational Autoencoder

Implementation of a Basic Variational Auto-Encoder

This repository aims to make analysis on human brain tissue (EM data). This work is done within the chair of Lichtman Lab. at Harvard University.

Final project for Bayesian Theory and Computation (2021 spring) @ PKU.

Deep generative models for controlled text generation.

unsupervised semantic segmentation for self driving cars with variational autoencoders, genetic algorithms and bayesian methods

Implementing Variational Autoencoder and explored the importance of each part of its loss function.

Handwritten Digit Generation with VAE and GAN are applied.

Demo Page for "Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech" (SLT22)

Implementation of generative models for the design of small molecules

Implementation of a Denoising Diffusion Probabilistic Model with some mathematical background.

Repo for all the SRIP 2024 work at CVIG Lab IITGN under Prof. Shanmuganathan Raman

Variational Autoencoder that is trained to generate or reconstruct audio of spoken digits from 0 to 9

Implementation of a Variational Autoencoder (VAE) for meandering river images using PyTorch

Synthesizing sequence of images by learning latent dynamics and VAE

Some coding stuff from various machine learning books

Implementation of Conv-AutoEncoder and Variational-AutoEncoder in TensorFlow/ keras

The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for the purpose of dimensionality reduction.

Variational Autoencoder with TensorFlow 2

A Research Project Using Generative models like Variational Autoencoder (VAE), T2-Weighted Images are being generated from T1-Weighted Images. Have achieved a maximum of 0.15 RMSE on validation dataset.