A Collection of Variational Autoencoders (VAE) in PyTorch.
-
Updated
Jun 13, 2024 - Python
A Collection of Variational Autoencoders (VAE) in PyTorch.
Variational auto-encoder trained on celebA . All rights reserved.
Get started with CelebA-HQ dataset in under 5 mins !
GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
Using Capsule Networks in GANS to generate very realistic fake images that could perhaps be used for deepfakes
Code repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)
Variational Autoencoder trained by Feature Perceputal Loss
👦 Human head semantic segmentation
Example of vanilla VAE for face image generation at resolution 128x128 using pytorch.
Code and notebooks related to the paper: "Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks" by VanRullen & Reddy, 2019
Who is your doppelgänger and more with Keras face recognition
Apply Thatcher illusion on a set of face photos
Generative Adversarial Networks in PyTorch
Official adversarial mixup resynthesis repository
This repository is related to a project of the Introduction to Numerical Imaging (i.e, Introduction à l'Imagerie Numérique in French), given by the MVA Masters program at ENS-Paris Saclay. It was entirely build from scratch and contains code in PyTorch Lightning to train and then use a neural network for image classification. We used it to creat…
Conditional VAE in Tensorflow 2 | Conditional Image Generation | CelebA dataset
Code for the paper "Transfer Learning for Facial Attribute Prediction and Clustering" (iSCI 2019)
Trained an End-to-End model for deblurring of celebrity faces (CelebA).
Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs (ACM CCS'21)
Add a description, image, and links to the celeba-dataset topic page so that developers can more easily learn about it.
To associate your repository with the celeba-dataset topic, visit your repo's landing page and select "manage topics."