GANocracy Tutorial Setup

Note: If you are unable to complete the setup or don't mind viewing the tutorial without the ability to interact with the content, we have made an NB viewer version of the GAN training notebook.

The following instructions provide the necessary configuration to run the Jupyter notebooks we’ll be using to explore a generator with GANdissect and train GANs. If you'd like to follow along on your own laptop, we strongly recommend that you complete these setup instructions before the tutorial.

Step-by-Step Instructions:

Step 1: Install Anaconda. While many systems come with Python already installed, it may not be the latest version. For example, macOS comes with Python 2.7 by default, but this is not supported by the tutorial.

We recommend downloading the Anaconda Distribution of Python 3. Anaconda comes with conda, a cross platform package and environment manager that facilitates installations and is required for setup for both notebooks.

macOS

  # Download installation scripts from Anaconda website:
  curl -O https://repo.anaconda.com/archive/Anaconda3-2019.03-MacOSX-x86_64.sh

  # Run the interactive installation script:
  sh Anaconda3-2019.03-MacOSX-x86_64.sh
        

Linux

  # Download installation scripts from Anaconda website:
  curl -O https://repo.anaconda.com/archive/Anaconda3-2019.03-Linux-x86_64.sh

  # Run the interactive installation script:
  sh Anaconda3-2019.03-Linux-x86_64.sh
        

Windows

  # Download installation scripts from Anaconda website:
  curl -O https://repo.anaconda.com/archive/Anaconda3-2019.03-Windows-x86_64.exe

  # Run the interactive installation script:
  sh Anaconda3-2019.03-Windows-x86_64.exe
        

Follow the prompts to complete the installation. The defaults are generally good.

Step 2: Verify your installation: If you accepted the defaults above, your system should now be using anaconda python by default. To verify, check that which conda, which pip and which python (on macOS/Linux) or where conda, where pip and where python (on Windows) all point to the correct path. Additionally, you can check your version of python with python --version.

Step 3: Complete the setup for each notebook: Both projects have their own set of requirements and different instructions to finish the setup:

• Explore a generator with GANdissect
• Training a GAN