Our group aims to learn about Variational Autoencoders by training a VAE model using Keras. The dataset we used was Fashion MNIST, a collection of 28x28 pixel images split into 10 classes of clothing items. We used the encoder model to output a visualization of the dataset’s latent space, and plotted similarity between images. To learn more about VAEs, we also analyzed the mathematical models behind concept, compared the method to autoencoders + PCA, and explored applications of VAE in domains other than image generation.
-
Notifications
You must be signed in to change notification settings - Fork 0
Our group aims to learn about Variational Autoencoders by training a VAE model using Keras. The dataset we used was Fashion MNIST, a collection of 28x28 pixel images split into 10 classes of clothing items. We used the encoder model to output a visualization of the dataset’s latent space, and plotted similarity between images. To learn more abou…
junanguo/VAE-On-Fashion-MNist
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Our group aims to learn about Variational Autoencoders by training a VAE model using Keras. The dataset we used was Fashion MNIST, a collection of 28x28 pixel images split into 10 classes of clothing items. We used the encoder model to output a visualization of the dataset’s latent space, and plotted similarity between images. To learn more abou…
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published