Dataset - LDM

dsprites: A Benchmark for Disentanglement in Unsupervised Learning

dsprites: A benchmark for disentanglement in unsupervised learning.
- Dataset
- JSON
ER Random Graphs

The dataset used in the paper is ER random graphs, which are generated by the Erdos-Renyi random graph model. The graphs are used to test the proposed β-VAE model for...
- Dataset
- JSON
Sprites

The Sprites dataset has 672 synthetically rendered animated characters (sprites). The dataset is split into a training set with 500, a validation set with 72, and a test set...
- Dataset
- JSON
dsprites: Disentangle-ment testing sprites dataset

The dataset used in the paper is dsprites: Disentangle-ment testing sprites dataset, which consists of 26,000 naturalistic object images.
- Dataset
- JSON
dsprites: Disentanglement testing sprites dataset

dsprites: Disentanglement testing sprites dataset
- Dataset
- JSON

You can also access this registry using the API (see API Docs).

5 datasets found