Autoencoders in Keras
-
Updated
Mar 6, 2018 - Python
Autoencoders in Keras
Count{down, up} with MNIST using Latent Interpolation
Witchcraft is a toolkit capable of encoding documents of various content types and structure (flat, hierarchical, or series) into searchable latent vector space.
Variational autoencoder for playing in the latent space
A project for understanding latent spaces in different neural networks (joint work with interns 2018)
Large-scale Dynamic Models of Complex Networks
Visualize the Latent Space of an Autoencoder using matplotlib
Controllable Face Generation via pretrained Conditional Adversarial Latent Autoencoder (ALAE)
Keras implementation of Variation Autoencoder for face generation. Analysis of the distribution of the latent space of the VAE. Vector arithemtic in the latent space. Morphing between the faces. The model was trained on CelebA dataset
This repository provides implementation simplified Variational Autoencoder (VAE), producing smooth latent space completely unsupervised manner. And this can be used as generative model as well.
Variational Autoencoders implementation in Keras.
Code accompanying ISMIR'19 paper titled "Learning to Traverse Latent Spaces for Musical Score Inpaintning"
A simple Jupyter notebook to visualize data in latent space using dimensionality reduction techniques.
Restricted Boltzmann Machines (RBMs) and Deep Belief Networks (DBNs) from scratch for representation learning on the MNIST dataset.
Replication of the research paper titled Auto-Encoding Variational Bayes.
Toy example for a Conditional Variational Autoencoder in Keras. Regresses features from automatically generated images. Useful for learning about the concept.
Visualization of the MNIST dataset as a neural network understands it through the traversal of the 2-D latent space. Powered by SeaLion.
Extension of GANspace: https://github.com/harskish/ganspace
Add a description, image, and links to the latent-space topic page so that developers can more easily learn about it.
To associate your repository with the latent-space topic, visit your repo's landing page and select "manage topics."