fashionMnist
fun fashionMnist(cacheDirectory: File = File("cache")): Pair<OnHeapDataset, OnHeapDataset>
Content copied to clipboard
Loads the Fashion-MNIST dataset.
This is a dataset of 60,000 28x28 grayscale images of 10 fashion categories, along with a test set of 10,000 images. This dataset can be used as a drop-in replacement for MNIST. The class labels are:
| Label | Description |
|---|---|
| 0 | T-shirt/top |
| 1 | Trousers |
| 2 | Pullover |
| 3 | Dress |
| 4 | Coat |
| 5 | Sandals |
| 6 | Shirt |
| 7 | Sneakers |
| 8 | Bag |
| 9 | Ankle boots |
NOTE: The copyright for Fashion-MNIST is held by Zalando SE. Fashion-MNIST is licensed under the MIT license.
Return
Train and test datasets. Each dataset includes X and Y data. X data are uint8 arrays of grayscale image data with shapes (num_samples, 28, 28). Y data uint8 arrays of digit labels (integers in range 0-9) with shapes (num_samples,).
Parameters
cacheDirectory
Cache directory to cached models and datasets.