Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
About
We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits. The dataset is freely available at https://github.com/zalandoresearch/fashion-mnist
Han Xiao, Kashif Rasul, Roland Vollgraf• 2017
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Classification | MNIST (test) | Accuracy96.9 | 894 | |
| Image Classification | MNIST (test) | Accuracy99 | 654 | |
| Image Classification | Fashion MNIST (test) | Accuracy89.7 | 633 | |
| Image Classification | FashionMNIST (test) | -- | 461 | |
| Image Classification | F-MNIST (test) | -- | 173 | |
| Image Classification | Fashion MNIST (test) | Accuracy (%)93.7 | 90 | |
| Image Classification | 2D Noisy XOR (test) | Accuracy0.8715 | 9 |
Showing 7 of 7 rows