ImageNet 64x64

The 64x64 ImageNet dataset is used for training a vector-quantized variational auto-encoder, encoding images into a tensor of latents.

Data and Resources

Cite this as

Matthew D. Hoffman, Dustin Tran, Srinivas Vasudevan, Alexey Radul, Matthew Johnson, Dave Moore, Christopher Suter, Rif A. Saurous (2024). Dataset: ImageNet 64x64. https://doi.org/10.57702/05xrlt26

DOI retrieved: November 25, 2024

Additional Info

Field Value
Created November 25, 2024
Last update November 25, 2024
Defined In https://doi.org/10.48550/arXiv.1811.02091
Author Matthew D. Hoffman
More Authors
Dustin Tran
Srinivas Vasudevan
Alexey Radul
Matthew Johnson
Dave Moore
Christopher Suter
Rif A. Saurous