Imagenet64 is a massive dataset of small images called the down-sampled version of Imagenet. Imagenet64 comprises 1,281,167 training data and 50,000 test data with 1,000 labels.
Source: A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
Image Source: https://patrykchrabaszcz.github.io/Imagenet32/
Variants: ImageNet-64
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Image Classification | WRN (N=36, k=5) | A Downsampled Variant of ImageNet … | 2017-07-27 |
Recent papers with results on this dataset:
