dacapo.experiments.tasks.predictors.affinities_predictor

Classes

AffinitiesPredictor

A predictor for generating affinity predictions from input data.

Module Contents

class dacapo.experiments.tasks.predictors.affinities_predictor.AffinitiesPredictor(neighborhood: List[funlib.geometry.Coordinate], lsds: bool = True, num_voxels: int = 20, downsample_lsds: int = 1, grow_boundary_iterations: int = 0, affs_weight_clipmin: float = 0.05, affs_weight_clipmax: float = 0.95, lsd_weight_clipmin: float = 0.05, lsd_weight_clipmax: float = 0.95, background_as_object: bool = False)

A predictor for generating affinity predictions from input data.

neighborhood

The neighborhood.

Type:: List[Coordinate]

lsds

Whether to compute local shape descriptors.

Type:: bool

num_voxels

The number of voxels.

Type:: int

downsample_lsds

The downsample rate for LSDs.

Type:: int

grow_boundary_iterations

The number of iterations to grow the boundary.

Type:: int

affs_weight_clipmin

The minimum weight for affinities.

Type:: float

affs_weight_clipmax

The maximum weight for affinities.

Type:: float

lsd_weight_clipmin

The minimum weight for LSDs.

Type:: float

lsd_weight_clipmax

The maximum weight for LSDs.

Type:: float

background_as_object

Whether to treat the background as an object.

Type:: bool

__init__(: self, neighborhood: List[Coordinate], lsds: bool = True, num_voxels: int = 20, downsample_lsds: int = 1, grow_boundary_iterations: int = 0, affs_weight_clipmin: float = 0.05, affs_weight_clipmax: float = 0.95, lsd_weight_clipmin: float = 0.05, lsd_weight_clipmax: float = 0.95, background_as_object: bool = False

): Initializes the AffinitiesPredictor.

extractor(self, voxel_size): Get the LSD extractor.

dims(): Get the number of dimensions.

sigma(self, voxel_size): Compute the sigma value for LSD computation.

lsd_pad(self, voxel_size): Compute the padding for LSD computation.

num_channels(): Get the number of channels.

create_model(self, architecture): Create the model.

create_target(self, gt): Create the target data.

_grow_boundaries(self, mask, slab): Grow the boundaries of the mask.

create_weight(self, gt, target, mask, moving_class_counts=None): Create the weight data.

gt_region_for_roi(self, target_spec): Get the ground truth region for the target region of interest (ROI).

output_array_type(): Get the output array type.

Notes

This is a subclass of Predictor.

neighborhood

lsds

num_voxels

grow_boundary_iterations

affs_weight_clipmin

affs_weight_clipmax

lsd_weight_clipmin

lsd_weight_clipmax

background_as_object

extractor(voxel_size)

Get the LSD extractor.

Parameters:: voxel_size (Coordinate) – The voxel size.
Returns:: The LSD extractor.
Return type:: LsdExtractor
Raises:: NotImplementedError – This method is not implemented.

Examples

>>> extractor = predictor.extractor(voxel_size)

property dims

Get the number of dimensions.

Returns:: The number of dimensions.
Return type:: int
Raises:: NotImplementedError – This method is not implemented.

Examples

>>> predictor.dims

sigma(voxel_size)

Compute the sigma value for LSD computation.

Parameters:: voxel_size (Coordinate) – The voxel size.
Returns:: The sigma value.
Return type:: Coordinate
Raises:: NotImplementedError – This method is not implemented.

Examples

>>> predictor.sigma(voxel_size)

lsd_pad(voxel_size)

Compute the padding for LSD computation.

Parameters:: voxel_size (Coordinate) – The voxel size.
Returns:: The padding value.
Return type:: Coordinate
Raises:: NotImplementedError – This method is not implemented.

Examples

>>> predictor.lsd_pad(voxel_size)

property num_channels

Get the number of channels.

Returns:: The number of channels.
Return type:: int
Raises:: NotImplementedError – This method is not implemented.

Examples

>>> predictor.num_channels

create_model(architecture)

Create the model.

Parameters:: architecture – The architecture for the model.
Returns:: The created model.
Return type:: Model
Raises:: NotImplementedError – This method is not implemented.

Examples

>>> model = predictor.create_model(architecture)

create_target(gt)

Create the target data.

Parameters:: gt – The ground truth data.
Returns:: The created target data.
Return type:: NumpyArray
Raises:: NotImplementedError – This method is not implemented.

Examples

>>> predictor.create_target(gt)

create_weight(gt, target, mask, moving_class_counts=None)

Create the weight data.

Parameters:

gt – The ground truth data.
target – The target data.
mask – The mask data.
moving_class_counts – The moving class counts.

Returns:

The created weight data and moving class counts.

Return type:

Tuple[NumpyArray, Tuple]

Raises:

NotImplementedError – This method is not implemented.

Examples

>>> predictor.create_weight(gt, target, mask, moving_class_counts)

gt_region_for_roi(target_spec)

Get the ground truth region for the target region of interest (ROI).

Parameters:: target_spec – The target region of interest (ROI) specification.
Returns:: The ground truth region specification.
Raises:: NotImplementedError – This method is not implemented.

property output_array_type

Get the output array type.

Returns:: The output array type.
Return type:: EmbeddingArray
Raises:: NotImplementedError – This method is not implemented.

Examples

>>> predictor.output_array_type