Skip to content

Latest commit

 

History

History
19 lines (10 loc) · 891 Bytes

datasets.md

File metadata and controls

19 lines (10 loc) · 891 Bytes

Datasets

We use tfrecord format data for this project.

Celeba

See convert_celeba.py for how to download and convert the dataset.

Getchu

The preprocessed dataset can be found here. We crop the images using an anime face detector.

See the "Towards the Automatic Anime Characters Creation with Generative Adversarial Networks" paper for details

Cats

Training set contains 8402 images and validation set contains 100 images. The dataset is generated from a modified version of Deep learning with cats

The preprocessed dataset can be found here.