dacapo.experiments.datasplits

Subpackages

• dacapo.experiments.datasplits.datasets
  • dacapo.experiments.datasplits.datasets.arrays
    • dacapo.experiments.datasplits.datasets.arrays.array
    • dacapo.experiments.datasplits.datasets.arrays.array_config
    • dacapo.experiments.datasplits.datasets.arrays.binarize_array
    • dacapo.experiments.datasplits.datasets.arrays.binarize_array_config
    • dacapo.experiments.datasplits.datasets.arrays.concat_array
    • dacapo.experiments.datasplits.datasets.arrays.concat_array_config
    • dacapo.experiments.datasplits.datasets.arrays.crop_array
    • dacapo.experiments.datasplits.datasets.arrays.crop_array_config
    • dacapo.experiments.datasplits.datasets.arrays.dummy_array
    • dacapo.experiments.datasplits.datasets.arrays.dummy_array_config
    • dacapo.experiments.datasplits.datasets.arrays.dvid_array
    • dacapo.experiments.datasplits.datasets.arrays.dvid_array_config
    • dacapo.experiments.datasplits.datasets.arrays.intensity_array
    • dacapo.experiments.datasplits.datasets.arrays.intensity_array_config
    • dacapo.experiments.datasplits.datasets.arrays.logical_or_array
    • dacapo.experiments.datasplits.datasets.arrays.logical_or_array_config
    • dacapo.experiments.datasplits.datasets.arrays.merge_instances_array
    • dacapo.experiments.datasplits.datasets.arrays.merge_instances_array_config
    • dacapo.experiments.datasplits.datasets.arrays.missing_annotations_mask
    • dacapo.experiments.datasplits.datasets.arrays.missing_annotations_mask_config
    • dacapo.experiments.datasplits.datasets.arrays.numpy_array
    • dacapo.experiments.datasplits.datasets.arrays.ones_array
    • dacapo.experiments.datasplits.datasets.arrays.ones_array_config
    • dacapo.experiments.datasplits.datasets.arrays.resampled_array
    • dacapo.experiments.datasplits.datasets.arrays.resampled_array_config
    • dacapo.experiments.datasplits.datasets.arrays.sum_array
    • dacapo.experiments.datasplits.datasets.arrays.sum_array_config
    • dacapo.experiments.datasplits.datasets.arrays.tiff_array
    • dacapo.experiments.datasplits.datasets.arrays.tiff_array_config
    • dacapo.experiments.datasplits.datasets.arrays.zarr_array
    • dacapo.experiments.datasplits.datasets.arrays.zarr_array_config
  • dacapo.experiments.datasplits.datasets.graphstores
    • dacapo.experiments.datasplits.datasets.graphstores.graph_source_config
  • dacapo.experiments.datasplits.datasets.dataset
  • dacapo.experiments.datasplits.datasets.dataset_config
  • dacapo.experiments.datasplits.datasets.dummy_dataset
  • dacapo.experiments.datasplits.datasets.dummy_dataset_config
  • dacapo.experiments.datasplits.datasets.raw_gt_dataset
  • dacapo.experiments.datasplits.datasets.raw_gt_dataset_config
• dacapo.experiments.datasplits.keys
  • dacapo.experiments.datasplits.keys.keys

Submodules

• dacapo.experiments.datasplits.datasplit
• dacapo.experiments.datasplits.datasplit_config
• dacapo.experiments.datasplits.datasplit_generator
• dacapo.experiments.datasplits.dummy_datasplit
• dacapo.experiments.datasplits.dummy_datasplit_config
• dacapo.experiments.datasplits.train_validate_datasplit
• dacapo.experiments.datasplits.train_validate_datasplit_config

Package Contents

Classes

DataSplit	Helper class that provides a standard way to create an ABC using
DataSplitConfig	A class used to create a DataSplit configuration object.
DummyDataSplit	A class for creating a simple train dataset and no validation dataset.
DummyDataSplitConfig	A simple class representing config for Dummy DataSplit.
TrainValidateDataSplit	Helper class that provides a standard way to create an ABC using
TrainValidateDataSplitConfig	This is the standard Train/Validate DataSplit config.
DataSplitGenerator	Generates DataSplitConfig for a given task config and datasets.

class dacapo.experiments.datasplits.DataSplit

Helper class that provides a standard way to create an ABC using inheritance.

train: List[dacapo.experiments.datasplits.datasets.Dataset]

validate: List[dacapo.experiments.datasplits.datasets.Dataset] | None

class dacapo.experiments.datasplits.DataSplitConfig

A class used to create a DataSplit configuration object.

name

A name for the datasplit. This name will be saved so it can be found and reused easily. It is recommended to keep it short and avoid special characters.

Type:

str

verify() → Tuple[bool, str]:

Validates if it is a valid data split configuration.

name: str

verify() → Tuple[bool, str]

Validates if the current configuration is a valid data split configuration.

Returns:

True if the configuration is valid, False otherwise along with respective validation error message.

Return type:

Tuple[bool, str]

class dacapo.experiments.datasplits.DummyDataSplit(datasplit_config)

A class for creating a simple train dataset and no validation dataset.

It is derived from DataSplit class.

… .. attribute:: train

The list containing training datasets. In this class, it contains only one dataset for training.

type:

list

validate

The list containing validation datasets. In this class, it is an empty list as no validation dataset is set.

Type:

list

__init__(self, datasplit_config):

The constructor for DummyDataSplit class. It initialises a list with training datasets according to the input configuration.

train: List[dacapo.experiments.datasplits.datasets.Dataset]

validate: List[dacapo.experiments.datasplits.datasets.Dataset]

class dacapo.experiments.datasplits.DummyDataSplitConfig

A simple class representing config for Dummy DataSplit.

This class is derived from ‘DataSplitConfig’ and is initialized with ‘DatasetConfig’ for training dataset.

datasplit_type

Class of dummy data split functionality.

train_config

Config for the training dataset. Defaults to DummyDatasetConfig.

datasplit_type

train_config: dacapo.experiments.datasplits.datasets.DatasetConfig

verify() → Tuple[bool, str]

A method for verification. This method always return ‘False’ plus a string indicating the condition.

Returns:

A tuple contains a boolean ‘False’ and a string.

Return type:

Tuple[bool, str]

class dacapo.experiments.datasplits.TrainValidateDataSplit(datasplit_config)

Helper class that provides a standard way to create an ABC using inheritance.

train: List[dacapo.experiments.datasplits.datasets.Dataset]

validate: List[dacapo.experiments.datasplits.datasets.Dataset]

class dacapo.experiments.datasplits.TrainValidateDataSplitConfig

This is the standard Train/Validate DataSplit config.

datasplit_type

train_configs: List[dacapo.experiments.datasplits.datasets.DatasetConfig]

validate_configs: List[dacapo.experiments.datasplits.datasets.DatasetConfig]

class dacapo.experiments.datasplits.DataSplitGenerator(name: str, datasets: List[DatasetSpec], input_resolution: funlib.geometry.Coordinate, output_resolution: funlib.geometry.Coordinate, targets: List[str] | None = None, segmentation_type: str | SegmentationType = 'semantic', max_gt_downsample=32, max_gt_upsample=4, max_raw_training_downsample=16, max_raw_training_upsample=2, max_raw_validation_downsample=8, max_raw_validation_upsample=2, min_training_volume_size=8000, raw_min=0, raw_max=255, classes_separator_caracter='&')

Generates DataSplitConfig for a given task config and datasets. class names in gt_dataset shoulb be within [] e.g. [mito&peroxisome&er] for mutiple classes or [mito] for one class Currently only supports:

• semantic segmentation.

Supports:

• 2D and 3D datasets.

• Zarr, N5 and OME-Zarr datasets.

• Multi class targets.

property class_name

check_class_name(class_name)

compute()

static generate_from_csv(csv_path: pathlib.Path, input_resolution: funlib.geometry.Coordinate, output_resolution: funlib.geometry.Coordinate, name: str | None = None, **kwargs)