A variational autoencoder (VAE) is a generative model that combines deep learning with Bayesian inference to learn compact latent representations of data. VAEs are widely used for image generation, anomaly detection, and data augmentation.
Collection of generative models in Tensorflow
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
Notebooks about Bayesian methods for machine learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
Deep probabilistic analysis of single-cell and spatial omics data
"Deep Generative Modeling": Introductory Examples
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)
My first Python repo with codes in Machine Learning, NLP and Deep Learning with Keras and Theano
Next RecSys Library
PyTorch implementation of normalizing flow models
A curated list of awesome work on VAEs, disentanglement, representation learning, and generative models.
Experiments for understanding disentanglement in VAE latent representations
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch
We propose a VAE-LSTM model as an unsupervised learning approach for anomaly detection in time series.
Variational autoencoders for collaborative filtering
Tensorflow implementation of variational auto-encoder for MNIST
This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch
Open-AI's DALL-E for large scale training in mesh-tensorflow.