mnist_png.tgz 15.68MB
Type: Dataset
Tags: fastai

Bibtex:
@article{,
title= {MNIST},
author= {LeCun et al., 1998a},
abstract= {Classic dataset of small (28x28) handwritten grayscale digits, developed in the 1990s for testing the most sophisticated models of the day; today, often used as a basic “hello world” for introducing deep learning. This fast.ai datasets version uses a standard PNG format instead of the special binary format of the original, so you can use the regular data pipelines in most libraries; if you want to use just a single input channel like the original, simply pick a single slice from the channels axis},
keywords= {fastai},
terms= {},
license= {},
superseded= {},
url= {http://yann.lecun.com/exdb/publis/index.html#lecun-98}
}

Hosted by users:

Send Feedback Start
   0.000007
DB Connect
   0.000269
Lookup hash in DB
   0.004092
Get torrent details
   0.000267
Get torrent details, finished
   0.000639
Get authors
   0.000054
Parse bibtex
   0.000187
Write header
   0.000606
get stars
   0.000339
home tab
   0.000331
render right panel
   0.000040
render ads
   0.000071
fetch current hosters
   0.002901
Done