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

folder small (2 files)
filetrain_32x32.tar 4.11GB
filevalid_32x32.tar 161.47MB
Type: Dataset
Tags:

Bibtex:
@article{,
title= {Downsampled ImageNet 32x32},
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)},
terms= {},
license= {},
superseded= {},
url= {http://image-net.org/small/download.php}
}

Hosted by users:

Send Feedback Start
   0.000014
DB Connect
   0.001510
Lookup hash in DB
   0.001558
Get torrent details
   0.000490
Get torrent details, finished
   0.000805
Get authors
   0.000039
Parse bibtex
   0.000157
Write header
   0.000955
get stars
   0.000405
home tab
   0.002521
render right panel
   0.000010
render ads
   0.001074
fetch current hosters
   0.001589
Done