emmekah Goto Github PK

3d-vae

A variational autoencoder for volumetric shape generation

activity-detection-using-variational-autoencoders

adversarialvariationalbayes

This repository contains the code to reproduce the core results from the paper "Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks".

coma

Convolutional Mesh Autoencoders for Generating 3D Faces

convmesh

Code for "Mesh-based Autoencoders for Localized Deformation Component Analysis", AAAI 2018

coupled-vae-improved-robustness-and-accuracy-of-a-variational-autoencoder

We present a coupled Variational Auto-Encoder (VAE) method that improves the accuracy and robustness of the probabilistic inferences on represented data. The new method models the dependency between input feature vectors (images) and weighs the outliers with a higher penalty by generalizing the original loss function to the coupled entropy function, using the principles of nonlinear statistical coupling. We evaluate the performance of the coupled VAE model using the MNIST dataset. Compared with the traditional VAE algorithm, the output images generated by the coupled VAE method are clearer and less blurry. The visualization of the input images embedded in 2D latent variable space provides a deeper insight into the structure of new model with coupled loss function: the latent variable has a smaller deviation and the output values are generated by a more compact latent space. We analyze the histograms of probabilities for the input images using the generalized mean metrics, in which increased geometric mean illustrates that the average likelihood of input data is improved. Increases in the -2/3 mean, which is sensitive to outliers, indicates improved robustness. The decisiveness, measured by the arithmetic mean of the likelihoods, is unchanged and -2/3 mean shows that the new model has better robustness.

cvae

Conditional Variational AutoEncoder (CVAE) PyTorch implementation

cvpr2018-shape-completion

CVPR 2018 paper "Learning 3D Shape Completion from Laser Scan Data with Weak Supervision".

daml-shape-completion

CVPR'18 implementation of (deterministic) amortized maximum likelihood (AML) for weakly-supervised shape completion.

deepbayes-2019

Practical assignments of the Deep|Bayes summer school 2019

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

flexible-variational-graph-auto-encoders

Comp790 Project: Generative Models in Machine Learning

gae

Implementation of Graph Auto-Encoders in TensorFlow

gaussianmixturemodel

Different implementations of gaussian mixture model (EM, Variational, MCMC)

generative_model_zoo

generative_models_tutorial_with_demo

Generative Models Tutorial with Demo: Bayesian Classifier Sampling, Variational Auto Encoder (VAE), Generative Adversial Networks (GANs), Popular GANs Architectures, Auto-Regressive Models, Important Generative Model Papers, Courses, etc..

geometric-computing-python

geometrics

Repo for the paper "GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects"

geometry-processing-csc2520

Course Page for Geometry Processing

gl3d

GL3D (Geometric Learning with 3D Reconstruction): a large-scale database created for 3D reconstruction and geometry-related learning problems

graph_convolutional_nn_molecule_maker

A Graph Neural Network (Geometric machine learning) for molecular generation

machine-learning

mesh

MPI-IS Mesh Processing Library

mesh-vae

Code for "Variational Autoencoders for Deforming 3D Mesh Models", CVPR 2018

moses

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

nonlinear_face_3dmm

Source code for "Nonlinear 3D Face Morphable Model"

pointnet-autoencoder

Autoencoder for Point Clouds

python-project-structure

A tutorial on how to manage a Python project

pytorch-vae

A Collection of Variational Autoencoders (VAE) in PyTorch.

pytorch_coma