Multi-Object Datasets

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".<br> 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.

多目标数据集（Multi-Object Datasets，https://github.com/deepmind/multi_object_datasets）经后处理优化，可便捷复现ICML'21论文《面向对称与解耦多目标表征学习的高效迭代摊销推理》中的训练与评估流程。CLEVR6、Multi-dSprites及Tetrominoes数据集均采用.h5格式存储，并按训练集与测试集划分，各数据集均提供图像与掩码数据。其中CLEVR6还包含用于解耦性评估的真实潜在因子。请将所提供的压缩包解压至指定路径。