Python specific core utilities for running models in the BioImage Model Zoo.

The bioimageio.core package can be installed from conda-forge via

conda install -c conda-forge bioimageio.core

if you don't install any additional deep learning libraries, you will only be able to use general convenience functionality, but not any functionality for model prediction. To install additional deep learning libraries use:

• Pytorch/Torchscript:

  # cpu installation (if you don't have an nvidia graphics card)
  conda install -c pytorch -c conda-forge bioimageio.core pytorch torchvision cpuonly
  
  # gpu installation (for cuda 11.6, please choose the appropriate cuda version for your system)
  conda install -c pytorch -c nvidia -c conda-forge bioimageio.core pytorch torchvision pytorch-cuda=11.6 

  Note that the pytorch installation instructions may change in the future. For the latest instructions please refer to pytorch.org.

• Tensorflow

  # currently only cpu version supported
  conda install -c conda-forge bioimageio.core tensorflow

• ONNXRuntime

  # currently only cpu version supported
  conda install -c conda-forge bioimageio.core onnxruntime

The package is also available via pip:

pip install bioimageio.core

To set up a development conda environment run the following commands:

conda env create -f dev/environment-base.yaml
conda activate bio-core-dev
pip install -e . --no-deps

There are different environment files that only install tensorflow or pytorch as dependencies available.

bioimageio.core installs a command line interface for testing models and other functionality. You can list all the available commands via:

bioimageio

Check that a model adheres to the model spec:

bioimageio validate <MODEL>

Test a model (including prediction for the test input):

bioimageio test-model <MODEL>

Run prediction for an image stored on disc:

bioimageio predict-image -m <MODEL> -i <INPUT> -o <OUTPUT>

Run prediction for multiple images stored on disc:

bioimagei predict-images -m <MODEL> -i <INPUT_PATTERN> - o <OUTPUT_FOLDER>

<INPUT_PATTERN> is a glob pattern to select the desired images, e.g. /path/to/my/images/*.tif.

bioimageio.core is a python library that implements loading models, running prediction with them and more. To get an overview of this functionality, check out the example notebooks:

• example/model_usage for how to load models and run prediction with them
• example/model_creation for how to create bioimage.io compatible model packages
• example/dataset_statistics_demo for how to use the dataset statistics for advanced pre-and-postprocessing

The model specification and its validation tools can be found at https://github.com/bioimage-io/spec-bioimage-io.