You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Este projeto implementa e treina uma Variational Autoencoder (VAE) usando dados de onda senoidal gerados artificialmente. O objetivo é avaliar a capacidade do VAE de reconstruir os dados de entrada e visualizar a diferença entre os dados originais e reconstruídos.
This repository contains notebooks with academic projects to practice and explore image creation using AI, where the use of VAE (Variational Autoencoders) and GANs (Generative Adversarial Networks) was explored to generate human faces based on a dataset with examples.
A variational Autoencoder (VAE) to generate human faces based on the CelebA dataset. A VAE is a generative model that learns to represent high-dimensional data (like images) in a lower-dimensional latent space, and then generates new data from this space.
Solutions for Advanced Image Analysis course assignments, featuring model designs for image summation and generation with MNIST, and style transfer using CycleGAN with MNIST and SVHN datasets.
Code for Bachelor Thesis "Unveiling Hidden Features: Multimodal Integration Using Cross-Modal Variational Autoencoders for the Identification of Stratification in ABIDE"