Lots of issues with MNIST, but most of all, it is really not representative of CV tasks. Please at least try CIFAR10, of comparable size.https://twitter.com/goodfellow_ian/status/852591106655043584 …
-
Besides, MNIST cannot serve as a benchmark to compare different ideas. But I suspect that's why people love it so much. Competing is hard.
On real datasets, you often need state-of-the-art results to prove your approach (which is unfortunate IMO). On MNIST, you don't have to.
-
-
That's the real problem imo , SITS results grab attention while non-SOTA papers are generally ignored.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I was shocked by MNIST non-real-worldness when I tried a few nets scoring great on MNIST against “mouse paint” web interface.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
basically in the same exact grid of the original dataset, you can draw a number and see the net scores for all the classes.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
nets scoring in the high 90s % are terrible at recognizing clearly written digits :-(
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.