Skip to content

Material for the tutorial: "Deep Diving into GANs: from theory to production"

License

Notifications You must be signed in to change notification settings

zurutech/gans-from-theory-to-production

Repository files navigation

Deep Diving into GANs: from theory to production

With our accrued experience with GANs, we would like to guide you through the required steps to go from theory to production with this revolutionary technology.

Starting from the very basic of what a GAN is, passing trough TensorFlow implementation, using the most cutting edge APIs available in the framework, and finally, production-ready serving at scale using Google Cloud Functions.

This is the ZURU Tech way of making GANs: enjoy it.

Workshop's Table of contents

  • Introduction to GANs: Theory and Applications (SlideShare)

    • Generator
    • Discriminator
    • Intuitive explaination
    • Non saturating value function
    • Models definition
    • Training phase
    • Types of GANs
    • Conditional GANs
    • Applications
      • Unconditional GAN
      • Conditional GAN
  • GANs in TensorFlow 2.0:

    • What does a GAN learn?
    • Input data
    • Generator and discriminator networks: Keras functional API
    • Define input and instantiate networks
    • The loss function and the training procedure
    • Discriminator loss function
    • Generator loss function
    • Gradient ascent
    • Visualize training
    • Advantages and disadvantages
    • Bonus exercise: converting it to a Conditional GAN
  • Writing a GAN using AshPy and TensorFlow Datasets

    • AshPy Essentials
    • tfds and AshPy input format
    • Getting the data ready to use
    • DCGAN Theory and Practice
      • Generator: from noise to insight
      • Deconvolution
      • Batch Normalization
      • Discriminator
      • Loss function: a bridge between two networks
    • Training
    • Tensorboard
    • Towards Serving
  • Production:

    • Serving Models using TF 2.0 and Cloud Functions
    • Web Demo: Generating and Interpolating Faces

Requirements

This tutorial requires the following packages:

Setting up the environment (Linux, MacOS)

Clone the repository

git clone https://github.com/zurutech/gans-from-theory-to-production
cd gans-from-theory-to-production

Prepare a virtual environment

  • virtualenv: virtualenv venv && source venv/bin/activate

Installing the required packages

pip install -r no-gpu-requirements.txt
# or pip install -r gpu-requirements if a GPU with Compute Capability >= 3.0 is present

Start your Jupyter server

jupyter notebook . or the newer jupyter lab ..


If you're here, you're ready to go.

Happy workshop!


We're hiring!

Do you just love machine learning and you're also interested in Computer Vision? Join us at ZURU Tech!

Authors