Downsampled ImageNet 64x64
Aaron van den Oord and Nal Kalchbrenner and Koray Kavukcuoglu

small (2 files)
train_64x64.tar 12.11GB
valid_64x64.tar 477.26MB
Type: Dataset
Tags:

Bibtex:
@article{,
title= {Downsampled ImageNet 64x64},
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superseded= {},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}
}

10 day statistics (4 downloads)

Average Time 2 hrs, 17 mins, 08 secs
Average Speed 1.53MB/s
Best Time 39 mins, 55 secs
Best Speed 5.26MB/s
Worst Time 4 hrs, 08 mins, 21 secs
Worst Speed 844.90kB/s
Report