Skip to content

This is my implementation of a special Variational Autoencoder under TF 2.0, which make it possible to squeeze N images to generate one single representation of all the dataset with colors segmentation of the difference objects

RayanAAY-ops/Variational-Autoencoder-For-Satellite-Imagery

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 

Repository files navigation

Segmenter Variational Autoencoder

This VAE has the ability to generate from within the distribution of satellites images a new image.

Hyperparameters

Hyperparameters Values
Epochs 2
batch size 32
learning rate 1e-4
dropout 0.5
mse_weight 1
KLDiv_weight 1e-3
Hidden activation SeLU
Latent activation Sigmoid

The dataset

Data represents satellites images of cities with multiples objects. Capture d’écran 2020-12-03 à 2 22 20 AM

Generative representation of the dataset

The resulted image shows interesting result, where objects are segmented with a specific color which make us able to distinguish an item from another. Capture d’écran 2020-12-03 à 2 31 58 AM

About

This is my implementation of a special Variational Autoencoder under TF 2.0, which make it possible to squeeze N images to generate one single representation of all the dataset with colors segmentation of the difference objects

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published