dacapo.experiments.tasks.post_processors

Submodules

Package Contents

Classes

DummyPostProcessor

Base class of all post-processors.

DummyPostProcessorParameters

Base class for post-processor parameters.

PostProcessorParameters

Base class for post-processor parameters.

PostProcessor

Base class of all post-processors.

ThresholdPostProcessor

Base class of all post-processors.

ThresholdPostProcessorParameters

Base class for post-processor parameters.

ArgmaxPostProcessor

Base class of all post-processors.

ArgmaxPostProcessorParameters

Base class for post-processor parameters.

WatershedPostProcessor

Base class of all post-processors.

WatershedPostProcessorParameters

Base class for post-processor parameters.
class dacapo.experiments.tasks.post_processors.DummyPostProcessor(detection_threshold: float)

Base class of all post-processors.

A post-processor takes a model’s prediction and converts it into the final output (e.g., per-voxel class probabilities into a semantic segmentation).

enumerate_parameters() → Iterable[dacapo.experiments.tasks.post_processors.dummy_post_processor_parameters.DummyPostProcessorParameters]

Enumerate all possible parameters of this post-processor. Should return instances of PostProcessorParameters.

set_prediction(prediction_array_identifier)
process(parameters, output_array_identifier, *args, **kwargs)

Convert predictions into the final output.

class dacapo.experiments.tasks.post_processors.DummyPostProcessorParameters

Base class for post-processor parameters.

min_size: int
class dacapo.experiments.tasks.post_processors.PostProcessorParameters

Base class for post-processor parameters.

property parameter_names: List[str]
id: int
class dacapo.experiments.tasks.post_processors.PostProcessor

Base class of all post-processors.

A post-processor takes a model’s prediction and converts it into the final output (e.g., per-voxel class probabilities into a semantic segmentation).

abstract enumerate_parameters() → Iterable[dacapo.experiments.tasks.post_processors.post_processor_parameters.PostProcessorParameters]

Enumerate all possible parameters of this post-processor.

abstract set_prediction(prediction_array_identifier: dacapo.store.local_array_store.LocalArrayIdentifier) → None
abstract process(parameters: dacapo.experiments.tasks.post_processors.post_processor_parameters.PostProcessorParameters, output_array_identifier: dacapo.store.local_array_store.LocalArrayIdentifier, num_workers: int = 16, chunk_size: funlib.geometry.Coordinate = Coordinate((64, 64, 64))) → dacapo.experiments.datasplits.datasets.arrays.Array

Convert predictions into the final output.

class dacapo.experiments.tasks.post_processors.ThresholdPostProcessor

Base class of all post-processors.

A post-processor takes a model’s prediction and converts it into the final output (e.g., per-voxel class probabilities into a semantic segmentation).

enumerate_parameters() → Iterable[dacapo.experiments.tasks.post_processors.threshold_post_processor_parameters.ThresholdPostProcessorParameters]

Enumerate all possible parameters of this post-processor.

set_prediction(prediction_array_identifier)
process(parameters: dacapo.experiments.tasks.post_processors.threshold_post_processor_parameters.ThresholdPostProcessorParameters, output_array_identifier: dacapo.store.array_store.LocalArrayIdentifier, num_workers: int = 16, block_size: daisy.Coordinate = Coordinate((256, 256, 256))) → dacapo.experiments.datasplits.datasets.arrays.zarr_array.ZarrArray

Convert predictions into the final output.

class dacapo.experiments.tasks.post_processors.ThresholdPostProcessorParameters

Base class for post-processor parameters.

threshold: float
class dacapo.experiments.tasks.post_processors.ArgmaxPostProcessor

Base class of all post-processors.

A post-processor takes a model’s prediction and converts it into the final output (e.g., per-voxel class probabilities into a semantic segmentation).

enumerate_parameters()

Enumerate all possible parameters of this post-processor. Should return instances of PostProcessorParameters.

set_prediction(prediction_array_identifier)
process(parameters, output_array_identifier: dacapo.store.array_store.LocalArrayIdentifier, num_workers: int = 16, block_size: daisy.Coordinate = Coordinate((256, 256, 256)))

Convert predictions into the final output.

class dacapo.experiments.tasks.post_processors.ArgmaxPostProcessorParameters

Base class for post-processor parameters.

class dacapo.experiments.tasks.post_processors.WatershedPostProcessor(offsets: List[funlib.geometry.Coordinate])

Base class of all post-processors.

A post-processor takes a model’s prediction and converts it into the final output (e.g., per-voxel class probabilities into a semantic segmentation).

enumerate_parameters()

Enumerate all possible parameters of this post-processor. Should return instances of PostProcessorParameters.

set_prediction(prediction_array_identifier)
process(parameters: dacapo.experiments.tasks.post_processors.watershed_post_processor_parameters.WatershedPostProcessorParameters, output_array_identifier: dacapo.store.array_store.LocalArrayIdentifier, num_workers: int = 16, block_size: funlib.geometry.Coordinate = Coordinate((256, 256, 256)))

Convert predictions into the final output.

class dacapo.experiments.tasks.post_processors.WatershedPostProcessorParameters

Base class for post-processor parameters.

bias: float
context: funlib.geometry.Coordinate