data

Download Datasets for Inpainting

FFHQ

• Repo: https://github.com/NVlabs/ffhq-dataset
• Kaggle command: kaggle datasets download -d rahulbhalley/ffhq-1024x1024

Places2

• Webpage: http://places2.csail.mit.edu
• Download Train: http://data.csail.mit.edu/places/places365/train_large_places365challenge.tar

ImageNet

• Webpage: https://www.image-net.org/challenges/LSVRC/2012/index.php#
• Kaggle link: https://www.kaggle.com/c/imagenet-object-localization-challenge/data?select=imagenet_object_localization_patched2019.tar.gz
• Kaggle command: kaggle competitions download -c imagenet-object-localization-challenge

WikiArt

• Kaggle: https://www.kaggle.com/c/painter-by-numbers/data
• Kaggle command: kaggle competitions download -c painter-by-numbers (It requires pip install kaggle==1.5.3)

Validation Set + Masks: https://polybox.ethz.ch/index.php/s/nBta4VE0uBjG65D

Validation Ground-Truth: https://polybox.ethz.ch/index.php/s/ishe5ocVOOvdiC3

Test Set + Masks: https://polybox.ethz.ch/index.php/s/qnf3NglUDqmvGBr

Test Ground-Truth: https://polybox.ethz.ch/index.php/s/vwT1xCPIOwbb6t7

It contains 1,000 images for each type of mask (7 x 1,000), for each dataset.