Multi-Object Datasets
Patrick Emami · Zenodo (CERN European Organization for Nuclear Research) · 2021
Multi-Object Datasets (https://github.com/deepmind/multi_object_datasets) post-processed for easy replication of the training and evaluation of the ICML'21 paper "Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations". Datasets for CLEVR6, Multi-dSprites, and Tetrominoes are in the .h5 format and split by training and test. Images and masks are provided for each. CLEVR6 also contains the ground truth latent factors for disentanglement evaluation. Unzip the provided zip file in the desired location.