Whole-slide image streamer for TensorFlow.
Project description
histomics_stream
Overview
The goal of this project is to create a whole-slide image file reader for machine learning with TensorFlow. This reader will allow users to extract pixel data from whole-slide image formats, and will support reading paradigms that are commonly used during training and inference.
Installation for Python
histomics_stream can be easily installed with Python wheels. If you do not want the installation to be to your current Python environment, you should first create and activate a Python virtual environment (venv) to work in. Then, run the following from the command line:
apt update
apt install -y python3-openslide openslide-tools
pip uninstall -y histomics_stream large_image tensorflow
pip install histomics_stream 'large_image[openslide,ometiff,openjpeg,bioformats]' --find-links https://girder.github.io/large_image_wheels
Launch python3, import the histomics_stream package, and use it
import histomics_stream as hs
This has been tested with tensorflow:2.6.2-gpu.
History
Through version 1.0.6, this project was known as tensorflow_reader.
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
Built Distribution
Hashes for histomics_stream-2.1.8-py2.py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 59571fbc959b5dfa89b29a2e82c7d17e8dfd75f31d5ffe9aa39f7cf55815fb47 |
|
| MD5 | 03fdd03a31e3258cf4f87fbba9e9dab5 |
|
| BLAKE2b-256 | c9781868d4289b9ab25dcc4f138c34bc986d1751742413e76275dbb772ecb1d6 |
