A small package for working with MNIST data.
Project description
MNIST Utils
This is a simple package for working with MNIST Images. If you have a physical mnist style gz file, you can use this package to load the images from the file.
This is useful for when you want to run a trained model for example and provide a PNG to the model. The model likely is trained on a numpy array -> this just handles the conversion from PNG to grayscale numpy array.
To get the latest version:
pip install mnist-utils
Working on the project
To build: python setup.py sdist bdist_wheel
To upload: python -m twine upload dist/*
(Token name: pypi_all_purpose)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
mnist-utils-0.0.2.tar.gz
(3.2 kB
view hashes)
Built Distribution
Close
Hashes for mnist_utils-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 146ef1e1911aef0a5f1a78ce2afa639ee0fe5a544c6a3edf7cdaa0aad6f9a3d0 |
|
MD5 | 55553d70592c3ec754b870e43de1c4c5 |
|
BLAKE2b-256 | 772f3f843b448cab69b6775642f2c9a82d358d74bec440f3fab56658ecf3da34 |