bioimageio.core

bioimageio.core is a python package that implements prediction with bioimage.io models including standardized pre- and postprocessing operations. Such models are represented as bioimageio.spec resource descriptions.

In addition bioimageio.core provides functionality to convert model weight formats and compute selected dataset statistics used for preprocessing.

Documentation

Here you find the bioimageio.core documentation.

Examples

Notebooks that save and load resource descriptions and validate their format (using bioimageio.spec, a dependency of bioimageio.core)

• load_model_and_create_your_own.ipynb
• dataset_creation.ipynb

Use the described resources in Python with bioimageio.core

• model_usage.ipynb

Presentations

• Create a model from scratch (source)

Set up Development Environment

To set up a development environment run the following commands:

conda create -n core python=$(grep -E '^requires-python' pyproject.toml | grep -oE '[0-9]+\.[0-9]+')
conda activate core
pip install -e .[dev,partners]

Joint development of bioimageio.spec and bioimageio.core

Assuming spec-bioimage-io is cloned to the parent folder a joint development environment can be created with the following commands:

conda create -n core python=$(grep -E '^requires-python' pyproject.toml | grep -oE '[0-9]+\.[0-9]+')
conda activate core
pip install -e .[dev,partners] -e ../spec-bioimage-io[dev]

Logging level

bioimageio.spec and bioimageio.core use loguru for logging, hence the logging level may be controlled with the LOGURU_LEVEL environment variable. The bioimageio CLI has logging enabled by default. To activate logging when using bioimageio.spec/bioimageio.core as a library, add

from loguru import logger

logger.enable("bioimageio")

Changelog

See changelog.md