05 Apr 2021

Fashion-MNIST is a machine learning benchmarking dataset created to replace MNIST, as MNIST is relatively easy to predict and therefore is not enough of a challenge to test different machine learning models.

One of the arguments mentioned by the creators at Zalando Research is that most pairs can be classified with just one pixel.

MNIST is too easy. Convolutional nets can achieve 99.7% on MNIST. Classic machine learning algorithms can also achieve 97% easily. Check out our side-by-side benchmark for Fashion-MNIST vs. …

Luca Franceschini

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store