Generative Adversarial Network(GAN) to recreate MNIST dataset.

[ShashankP19]

Description

In a Generative Adversarial Network (GAN), one neural network, called the generator, generates new data instances, while the other, the discriminator, evaluates them for authenticity; i.e. the discriminator decides whether each instance of data it reviews belongs to the actual training dataset or not. Build a Generative Adversarial Network(GAN) to recreate MNIST dataset. It should consist of two networks - the generator network and discriminator network.

Details

• Technical Specifications: python, tensorflow, keras
• Type of issue: Single
• Time Limit: 5 days

Issue requirements / progress

• [ ] Create a generator network
• [ ] Create a discriminator network
• [ ] Combine the generator and discriminator networks

Resources

• MNIST dataset
• A Beginner's Guide to Generative Adversarial Networks (GANs)
• Demystifying Generative Adversarial Nets (GANs)
• Generative Adversarial Networks — Explained

Directory Structure

Place your solution in /machine_learning/gan/mnist/<your_solution_file>

Note

Please claim the issue first by commenting here before starting to work on it.

[MuriloAndre2000]

I already did one, a DCGAN, if you want a gan to work with your data, I can share this one. To a mnist gan I have to prepare it