There are 2 repositories under gumbel-softmax topic.
A Collection of Variational Autoencoders (VAE) in PyTorch.
Pytorch implementation of JointVAE, a framework for disentangling continuous and discrete factors of variation :star2:
Implementation of NeurIPS 19 paper: Paraphrase Generation with Latent Bag of Words
Code for "Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection", ECCV 2022
Codes for "Deep Joint Source-Channel Coding for Wireless Image Transmission with Adaptive Rate Control", ICASSP 2022
TensorFlow GAN implementation using Gumbel Softmax
An implementation of a Variational-Autoencoder using the Gumbel-Softmax reparametrization trick in TensorFlow (tested on r1.5 CPU and GPU) in ICLR 2017.
Keras implementation of a Variational Auto Encoder with a Concrete Latent Distribution
TensorFlow-based implementation of "Attend, Infer, Repeat" paper (Eslami et al., 2016, arXiv:1603.08575).
Code for TACL 2022 paper on Data-to-text Generation with Variational Sequential Planning
Implementation of the Gumbel-Sigmoid distribution in PyTorch.
Official project of DiverseSampling (ACMMM2022 Paper)
Black-box spike and slab variational inference, example with linear models
The implementation of Gumbel softmax reparametrization trick for discrete VAE
Keras, Tensorflow eager execution implementation of Categorical Variational Autoencoder
Python library for the differentiable hypergeometric distribution
Jittor reimplementation of DiverseSampling (MM22)
[Pytorch] Minimal implementation of a Variational Autoencoder (VAE) with Categorical Latent variables inspired from "Categorical Reparameterization with Gumbel-Softmax".
Code acompanying the paper Developmentally motivated emergence of compositional communication via template transfer
collections of examples of gumbel softmax tricks in optimization & deep learning