https://github.com/gusgad/capsule-GAN

Code for my Master thesis on "Capsule Architecture as a Discriminator in Generative Adversarial Networks".
https://github.com/gusgad/capsule-GAN

capsnet capsule-network gan generative-adversarial-network keras python

Last synced: 8 days ago
JSON representation

Code for my Master thesis on "Capsule Architecture as a Discriminator in Generative Adversarial Networks".

• Host: GitHub
• URL: https://github.com/gusgad/capsule-GAN
• Owner: gusgad
• License: mit
• Created: 2018-01-05T10:16:18.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2023-06-07T16:31:11.000Z (over 1 year ago)
• Last Synced: 2024-08-01T08:11:41.300Z (3 months ago)
• Topics: capsnet, capsule-network, gan, generative-adversarial-network, keras, python
• Language: Jupyter Notebook
• Homepage: https://drive.google.com/file/d/15g9VFyGwjPnGcTzjXEDwvGpfNvPuRXqB/view?usp=sharing
• Size: 1.71 MB
• Stars: 127
• Watchers: 8
• Forks: 39
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-CapsNet - gusgad/capsule-GAN
• awesome-capsule-networks - gusgad/capsule-GAN

README

        
# Capsule GAN

[Link to the paper](https://drive.google.com/file/d/15g9VFyGwjPnGcTzjXEDwvGpfNvPuRXqB/view?usp=sharing)

Code for my Master thesis on "Capsule Layer as a Discriminator in Generative Adversarial Networks". In order to reproduce results, follow the "capsule_gan" Jupyter notebook that contains:

* Dataset loading and preprocessing

* Both Discriminator and Generator structures

* Training, loss functions

* Image outputs

* Metrics visualization

***

But first you may want to install [Miniconda](https://conda.io/miniconda.html) and corresponding dependencies from environment.yml:

`conda env create -f environment.yml` within the project directory as well as install [required tools for GPU computing](https://www.tensorflow.org/install/install_windows#requirements_to_run_tensorflow_with_gpu_support). If no GPU is going to be used - delete the `tensorflow-gpu` line from environment.yml.

### Generated images

![MNIST_output](/out_metrics/mnist_output_sample.png?raw=true)

![CIFAR10_output](/out_metrics/cifar10_output_sample.png?raw=true)

[All generated MNIST images over 30k epochs](https://www.amazon.com/clouddrive/share/BKlDzoKMhrFnIQu9LqH7KcrYvP9ZKoZF1oc5wjMPFRc)

[All generated CIFAR10 images over 30k epochs](https://www.amazon.com/clouddrive/share/V99W1XhuDg0U7ZABNXwtHBVaacMzqdUCKkI6m9Vp4HG)

[Generator weights for MNIST](https://www.amazon.com/clouddrive/share/wSRq5KX7IrWKaxvdsyGZubh9WcffzrfEFW89mEgQdLC)

[Generator weights for CIFAR10](https://www.amazon.com/clouddrive/share/2CKaZZdGlJqyT5WXnYu1Zbka1Vldtr9yCNffYWwz8Wn)

Thanks to @eriklindernoren () who I borrowed the Keras implementation of DCGAN from and @XifengGuo () who I took the squashing function from.