mnists

downloads and prepares various mnist-compatible datasets.

files are downloaded to ~/.mnist and checked for integrity by sha256 hashes.

dependencies: numpy

install: pip install --upgrade --upgrade-strategy only-if-needed mnists

I've added --upgrade-strategy to the command-line so you don't accidentally "upgrade" numpy to a version not compiled specifically for your system.

usage

import mnists

dataset = "emnist_balanced"
train_images, train_labels, test_images, test_labels = mnists.prepare(dataset)

the default output shape is (n, 1, 28, 28). pass flatten=True to mnists.prepare to get (n, 784).

datasets

in alphabetical order:

emnist

• emnist_balanced
• emnist_byclass
• emnist_bymerge
• emnist_digits
• emnist_letters
• emnist_mnist

fashion-mnist

• fashion_mnist

mnist

• mnist