National Gallery of Art Open Data Program tf.data.Dataset Loader

a tf.data Loader for the National Gallery of Art Open Data Program

... and Generative Modeling to Accompany!

Table of Contents

• Overview
• Quickstart
• Examples
• Citation

Quickstart

Getting started with the goa_loader loader is as easy as:

pip install goa-loader

Then you can load the dataset with:

dataset = goa_loader.load()

To make sure your installation works, try out:

python examples/basic/visualize_samples.py

Overview

goa_loader.load() loads a dataset of images from the National Gallery of Art Open Data Program into a tf.data.Dataset. This dataset may be used for anything; from generative modeling to style transfer. Check out Quickstart or examples/ to see how you can get started.

By Luke Wood & others

Background: National Gallery of Art Open Data Program

The National Gallery of Art Open Data Program has an official Github repo

The National Gallery of Art serves the United States by welcoming all people to explore and experience art, creativity, and our shared humanity. In pursuing our mission, we are making certain data about our collection available to scholars, educators, and the general public in CSV format to support research, teaching, and personal enrichment; to promote interdisciplinary research; to encourage fun and creativity; and to help people understand the inspiration behind great works of art. We hope that access to this dataset will fuel knowledge, scholarship, and innovation, inspiring uses that transform the way we discover and understand the world of art.

To the extent permitted by law, the National Gallery of Art waives any copyright or related rights that it might have in this dataset and is releasing this dataset under the Creative Commons Zero designation.

The dataset provides data records relating to the 130,000+ artworks in our collection and the artists who created them. You can download the dataset free of charge without seeking authorization from the National Gallery of Art.

Examples

• Basic Loading and Visualization
• Denoising Diffusion Implicit Model

Citation

@misc{goawood2022,
  title={A tf.data Loader for the National Gallery of Art Open Data Program},
  author={Wood, Luke and others},
  year={2022},
  howpublished={\url{https://github.com/lukewood/goa-loader}},
}