Downsampled ImageNet 32x32
Koray Kavukcuoglu and Aaron van den Oord and Nal Kalchbrenner

@article{,
title= {Downsampled ImageNet 32x32},
year= {2017},
keywords= {},
author= {Aaron van den Oord and Nal Kalchbrenner and Koray Kavukcuoglu},
abstract= {This page includes downsampled ImageNet images, which can be used for density estimation and generative modeling experiments. Images come in two resolutions: 32x32 and 64x64, and were introduced in Pixel Recurrent Neural Networks. Please refer to the Pixel RNN paper for more details and results. 

![](https://i.imgur.com/s6gdDuX.jpg)

**Reference:** Chrabaszcz, Loshchilov and Hutter, A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets. 2017. https://arxiv.org/abs/1707.08819},
terms= {},
license= {},
superseded= {},
url= {http://image-net.org/small/download.php}
}