https://github.com/vermavinay982/autoencoder-super-resolution

Experiment to enhance image resolutions without GANs by using autoencoder. Input being a small image.
https://github.com/vermavinay982/autoencoder-super-resolution

autoencoder deep-learning keras resolution

Last synced: 9 days ago
JSON representation

Experiment to enhance image resolutions without GANs by using autoencoder. Input being a small image.

• Host: GitHub
• URL: https://github.com/vermavinay982/autoencoder-super-resolution
• Owner: vermavinay982
• Created: 2021-02-22T16:35:13.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-06-26T18:15:06.000Z (over 3 years ago)
• Last Synced: 2024-10-14T14:11:30.264Z (24 days ago)
• Topics: autoencoder, deep-learning, keras, resolution
• Language: Jupyter Notebook
• Homepage:
• Size: 5.19 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Increase_Resolution_AutoEncoder

They were invented to help

1. Hidden layer to learn more robust features

2. Reduce risk of overfitting in autoencoder

3. Prevent autoencoder to learn a simple identity function (that would make it just repeat what is entered into the input)

## Features of AutoEncoder

1. Denoise the image using DeepLearning

2. Anomaly Detection with Keras, Tensorflow, Deep Learning

3. Compressing the image to a latent space

![](assets/10epc_grid_target_ip.png)

![](assets/10epc_grid_target_op.png)