Skip to main content

A package for doing hyper-spectral image augmentation for deep learning.

Project description

HYPer-spectral Image Augmentation (hypia)

The following is a Python package (available through the Python Package Manager (pip)) for the augmentation of hyper-spectral images for uses in deep learning.

Why does this exist?

  • Other image augmentation libraries often only accept RGB or grayscale images (with options for RGBA images usually too). However, in a scientific context, we often have images with more than 3/4 channels (so-called hyper-spectral imaging) and it seemed like a good idea to have an augmentation library which deals with all channels in parallel.
  • Another problem is that some image augmentation frameworks can accept more than 3/4 channels but convert the data to unsigned 8-bit integers (see PyTorch's torchvision) which is damaging for scientific data where we care about the actual numbers of the data. This can lead to the images losing some of the features and relative contrasts of features which is important for our science.

I had a look at several image augmentation packages but none of them seemed to satisfy both of these criteria so here we are.

Installation

There are two ways to install this package: either from pip or from source from GitHub.

From pip:

>>> pip install hypia

From GitHub:

>>> git clone https://github.com/rhero12/hypia
>>> cd hypia
>>> python setup.py install

Documentation

The documentation (including examples) is available here.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hypia-0.0.3.tar.gz (6.9 kB view details)

Uploaded Source

Built Distribution

hypia-0.0.3-py3-none-any.whl (8.2 kB view details)

Uploaded Python 3

File details

Details for the file hypia-0.0.3.tar.gz.

File metadata

  • Download URL: hypia-0.0.3.tar.gz
  • Upload date:
  • Size: 6.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.7.3

File hashes

Hashes for hypia-0.0.3.tar.gz
Algorithm Hash digest
SHA256 31bfecb9800b4471c834687c821b5d665115e5ff736568e4f08f9deb822fd4c7
MD5 d2147771347141c4a4811903de67714f
BLAKE2b-256 da816ba2e6e13b209ef6350910867550a4c797300f2b12e1d92f4485ff1c72ae

See more details on using hashes here.

File details

Details for the file hypia-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: hypia-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 8.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.7.3

File hashes

Hashes for hypia-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 38eb5e156f5eab451f60a25cacc4943f5f85065face54f2ff3ba0a1bb24a737e
MD5 0bf4c0c54ea1f442dad14a096dc23070
BLAKE2b-256 64bad2e81a9b8012dc9f1139c96cdc98713fc91f1a42b5db741ab9e1293e1a02

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page