https://github.com/soumik12345/generative-adversarial-networks

Implementations of various architectures and implementations of Generative Adversarial Networks
https://github.com/soumik12345/generative-adversarial-networks

conditional-gan convolutional-neural-networks gan generative-adversarial-network keras multilayer-perceptron neural-network python tensorflow wasserstein-gan

Last synced: 15 days ago
JSON representation

Implementations of various architectures and implementations of Generative Adversarial Networks

• Host: GitHub
• URL: https://github.com/soumik12345/generative-adversarial-networks
• Owner: soumik12345
• Created: 2019-04-29T07:27:25.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2022-11-21T21:30:08.000Z (almost 2 years ago)
• Last Synced: 2024-10-04T19:48:16.331Z (about 1 month ago)
• Topics: conditional-gan, convolutional-neural-networks, gan, generative-adversarial-network, keras, multilayer-perceptron, neural-network, python, tensorflow, wasserstein-gan
• Language: Jupyter Notebook
• Homepage:
• Size: 49 MB
• Stars: 2
• Watchers: 2
• Forks: 1
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Generative Adversarial Networks

### 1. [MLP-GAN](./1-MLP-GAN/)

Simple Generative Adversarial Network implemented using Multi Layered Perceptrons and trained on the MNIST dataset. The model can be generated by running the notebooks in the [notebooks](./1-MLP-GAN/notebooks/) folder. To test the pre-trained model run the `test_model.py` script.

Kaggle Kernel Link: [https://www.kaggle.com/soumikrakshit/generative-adversarial-network-in-tensorflow](https://www.kaggle.com/soumikrakshit/generative-adversarial-network-in-tensorflow)

![MLP-GAN](./1-MLP-GAN/mlp-gan.png)

### 2. [DCGAN](./2-DCGAN/)

Generative Adversarial Network implemented using Deep Convolutional Networks and trained on the MNIST dataset. The model can be generated by running the notebooks in the [notebooks](./2-DCGAN/notebooks/) folder. To test the pre-trained model run the `test_model.py` script.

Kaggle Kernel Link: [https://www.kaggle.com/soumikrakshit/dcgan-in-tensorflow](https://www.kaggle.com/soumikrakshit/dcgan-in-tensorflow)

![DCGAN](./2-DCGAN/dcgan.png)

### 3. [ACGAN](./3-ACGAN/)

Auxiliary Classifier Generative Adversarial Network implemented using Deep Convolutional Networks and trained on the MNIST dataset. The model can be generated by running the notebooks in the [notebooks](./3-ACGAN/notebooks/) folder. To test the pre-trained model run the `test_model.py` script.

Kaggle Kernel Link: [https://www.kaggle.com/soumikrakshit/auxiliary-classifier-gan](https://www.kaggle.com/soumikrakshit/auxiliary-classifier-gan)

![DCGAN](./3-ACGAN/acgan.png)

### 4. [WGAN](./4-WGAN/)

Generative Adversarial Network implemented using Deep Convolutional Networks and Wassertein's Loss Function trained on the MNIST dataset. The model can be generated by running the notebooks in the [notebooks](./4-WGAN/notebooks/) folder. To test the pre-trained model run the `test_model.py` script.

Kaggle Kernel Link: [https://www.kaggle.com/soumikrakshit/wassertein-gan](https://www.kaggle.com/soumikrakshit/wassertein-gan)

![WGAN](./4-WGAN/wgan.png)