proc_setup

Classes:

Name	Description
PreAndPostprocessing
RequiredDatasetMeasures
RequiredMeasures
RequiredSampleMeasures

Functions:

Name	Description
get_pre_and_postprocessing	Creates callables to apply pre- and postprocessing in-place to a sample
get_required_dataset_measures
get_requried_measures
get_requried_sample_measures
setup_pre_and_postprocessing	Get pre- and postprocessing operators for a model description.

Attributes:

Name	Type	Description
TensorDescr

TensorDescr module-attribute

TensorDescr = Union[v0_4.InputTensorDescr, v0_4.OutputTensorDescr, v0_5.InputTensorDescr, v0_5.OutputTensorDescr]

PreAndPostprocessing

Bases: NamedTuple

              flowchart TD
              bioimageio.core.proc_setup.PreAndPostprocessing[PreAndPostprocessing]

              

              click bioimageio.core.proc_setup.PreAndPostprocessing href "" "bioimageio.core.proc_setup.PreAndPostprocessing"
            

Returned by:

• API Reference  proc_setup  setup_pre_and_postprocessing

Attributes:

Name	Type	Description
post	List[Processing]
pre	List[Processing]

post instance-attribute

post: List[Processing]

pre instance-attribute

pre: List[Processing]

RequiredDatasetMeasures

Bases: NamedTuple

              flowchart TD
              bioimageio.core.proc_setup.RequiredDatasetMeasures[RequiredDatasetMeasures]

              

              click bioimageio.core.proc_setup.RequiredDatasetMeasures href "" "bioimageio.core.proc_setup.RequiredDatasetMeasures"
            

Returned by:

• API Reference  proc_setup  get_required_dataset_measures

Attributes:

Name	Type	Description
post	Set[DatasetMeasure]
pre	Set[DatasetMeasure]

post instance-attribute

post: Set[DatasetMeasure]

pre instance-attribute

pre: Set[DatasetMeasure]

RequiredMeasures

Bases: NamedTuple

              flowchart TD
              bioimageio.core.proc_setup.RequiredMeasures[RequiredMeasures]

              

              click bioimageio.core.proc_setup.RequiredMeasures href "" "bioimageio.core.proc_setup.RequiredMeasures"
            

Returned by:

• API Reference  proc_setup  get_requried_measures

Attributes:

Name	Type	Description
post	Set[Measure]
pre	Set[Measure]

post instance-attribute

post: Set[Measure]

pre instance-attribute

pre: Set[Measure]

RequiredSampleMeasures

Bases: NamedTuple

              flowchart TD
              bioimageio.core.proc_setup.RequiredSampleMeasures[RequiredSampleMeasures]

              

              click bioimageio.core.proc_setup.RequiredSampleMeasures href "" "bioimageio.core.proc_setup.RequiredSampleMeasures"
            

Returned by:

• API Reference  proc_setup  get_requried_sample_measures

Attributes:

Name	Type	Description
post	Set[SampleMeasure]
pre	Set[SampleMeasure]

post instance-attribute

post: Set[SampleMeasure]

pre instance-attribute

pre: Set[SampleMeasure]

get_pre_and_postprocessing

get_pre_and_postprocessing(model: AnyModelDescr, *, dataset_for_initial_statistics: Iterable[Sample], keep_updating_initial_dataset_stats: bool = False, fixed_dataset_stats: Optional[Mapping[DatasetMeasure, MeasureValue]] = None) -> _ProcessingCallables

Creates callables to apply pre- and postprocessing in-place to a sample

Source code in src/bioimageio/core/proc_setup.py

def get_pre_and_postprocessing(
    model: AnyModelDescr,
    *,
    dataset_for_initial_statistics: Iterable[Sample],
    keep_updating_initial_dataset_stats: bool = False,
    fixed_dataset_stats: Optional[Mapping[DatasetMeasure, MeasureValue]] = None,
) -> _ProcessingCallables:
    """Creates callables to apply pre- and postprocessing in-place to a sample"""

    setup = setup_pre_and_postprocessing(
        model=model,
        dataset_for_initial_statistics=dataset_for_initial_statistics,
        keep_updating_initial_dataset_stats=keep_updating_initial_dataset_stats,
        fixed_dataset_stats=fixed_dataset_stats,
    )
    return _ProcessingCallables(_ApplyProcs(setup.pre), _ApplyProcs(setup.post))

get_required_dataset_measures

get_required_dataset_measures(model: AnyModelDescr) -> RequiredDatasetMeasures

Source code in src/bioimageio/core/proc_setup.py

def get_required_dataset_measures(model: AnyModelDescr) -> RequiredDatasetMeasures:
    s = _prepare_setup_pre_and_postprocessing(model)
    return RequiredDatasetMeasures(
        {m for m in s.pre_measures if isinstance(m, DatasetMeasureBase)},
        {m for m in s.post_measures if isinstance(m, DatasetMeasureBase)},
    )

get_requried_measures

get_requried_measures(model: AnyModelDescr) -> RequiredMeasures

Source code in src/bioimageio/core/proc_setup.py

def get_requried_measures(model: AnyModelDescr) -> RequiredMeasures:
    s = _prepare_setup_pre_and_postprocessing(model)
    return RequiredMeasures(s.pre_measures, s.post_measures)

get_requried_sample_measures

get_requried_sample_measures(model: AnyModelDescr) -> RequiredSampleMeasures

Source code in src/bioimageio/core/proc_setup.py

def get_requried_sample_measures(model: AnyModelDescr) -> RequiredSampleMeasures:
    s = _prepare_setup_pre_and_postprocessing(model)
    return RequiredSampleMeasures(
        {m for m in s.pre_measures if isinstance(m, SampleMeasureBase)},
        {m for m in s.post_measures if isinstance(m, SampleMeasureBase)},
    )

setup_pre_and_postprocessing

setup_pre_and_postprocessing(model: AnyModelDescr, dataset_for_initial_statistics: Iterable[Sample], keep_updating_initial_dataset_stats: bool = False, fixed_dataset_stats: Optional[Mapping[DatasetMeasure, MeasureValue]] = None) -> PreAndPostprocessing

Get pre- and postprocessing operators for a model description. Used in `bioimageio.core.create_prediction_pipeline

Source code in src/bioimageio/core/proc_setup.py

def setup_pre_and_postprocessing(
    model: AnyModelDescr,
    dataset_for_initial_statistics: Iterable[Sample],
    keep_updating_initial_dataset_stats: bool = False,
    fixed_dataset_stats: Optional[Mapping[DatasetMeasure, MeasureValue]] = None,
) -> PreAndPostprocessing:
    """
    Get pre- and postprocessing operators for a `model` description.
    Used in `bioimageio.core.create_prediction_pipeline"""
    prep, post, prep_meas, post_meas = _prepare_setup_pre_and_postprocessing(model)

    missing_dataset_stats = {
        m
        for m in prep_meas | post_meas
        if fixed_dataset_stats is None or m not in fixed_dataset_stats
    }
    if missing_dataset_stats:
        initial_stats_calc = StatsCalculator(missing_dataset_stats)
        for sample in dataset_for_initial_statistics:
            initial_stats_calc.update(sample)

        initial_stats = initial_stats_calc.finalize()
    else:
        initial_stats = {}

    prep.insert(
        0,
        UpdateStats(
            StatsCalculator(prep_meas, initial_stats),
            keep_updating_initial_dataset_stats=keep_updating_initial_dataset_stats,
        ),
    )
    if post_meas:
        post.insert(
            0,
            UpdateStats(
                StatsCalculator(post_meas, initial_stats),
                keep_updating_initial_dataset_stats=keep_updating_initial_dataset_stats,
            ),
        )

    if fixed_dataset_stats:
        prep.insert(0, AddKnownDatasetStats(fixed_dataset_stats))
        post.insert(0, AddKnownDatasetStats(fixed_dataset_stats))

    return PreAndPostprocessing(prep, post)