History
Abstract
Fashion-MNIST is a modern drop-in replacement for MNIST. Released by Zalando Research in 2017, it packs 70 000 tiny grayscale images of apparel—sneakers, shirts, coats—into a lightweight benchmark. Its familiar format keeps setup trivial, while richer visuals pose a tougher challenge.
Origins
Zalando’s quality-control cameras captured millions of 96 × 96 product shots. Han Xiao et al. down-sampled these to 28 × 28, grouped them into ten balanced classes, and open-sourced the result. The idea: upgrade MNIST difficulty without touching loaders or evaluation scripts.
This page is for finding a classifier on the KMNIST dataset. This dataset is more challenging than the original MNIST dataset that I have previously solved.
The details of the dataset can be found in the associated paper.
In short, since the reformation of the Japanese education in 1868, there became a standardisation of the kanji characters, and in the present day, most Japanese people cannot read the texts from 150 years ago.