Generative Adversary Networks (GANs) are architectures of deep neural networks composed of two networks pitted against each other. This is one of the newest and most fascinating architectures in Deep Learning.
This project aims to show the application of the network in some conventional datasets.
Result after 1000 seasons in the mnist dataset
Result after 2000 seasons in the Fashion Mnist dataset
cd gan-network-experiment
docker-compose up -d --build
Go to #local-ip#:8111/lab and run the "gan-network-experiments.ipynb" notebook to observe the exploration process
- Include more experiments with different datasets