neuralib.stardist.base.AbstractSegmentationOptions

class neuralib.stardist.base.AbstractSegmentationOptions[source]

Bases: AbstractParser

__init__()

Methods

`__init__`()
`eval`()	eval the model in single file or batch files in directory, and save the results
`foreach_process_image`([to_gray])	Iterates over image files in the specified directory, processes each image, and yields the file path along with the processed image.
`ij_roi_output`(filepath)	Get imageJ/Fiji `.roi` output save path
`launch_napari`(**kwargs)	run napari GUI viewer
`main`([args, parse_only, system_exit])	parsing the commandline input args and call `run()`.
`new_parser`(**kwargs)	create an `ArgumentParser`.
`process_image`([to_gray])	Process the image for segmentation.
`run`()	called after `main()`.
`seg_output`(filepath)	Get segmented output save path

Attributes

`DESCRIPTION`	parser description.
`EPILOG`	parser epilog.
`EX_GROUP_SOURCE`
`GROUP_IO`
`USAGE`	parser usage.
`batch_mode`	flag batch mode
`directory`	directory for batch imaging processing
`directory_suffix`	suffix in the directory for batch mode (default: '.tif')
`file`	image file path
`file_mode`	flag file mode
`invalid_existed_result`	force re-evaluate the result (default: False)
`model`	which pretrained model for evaluation
`napari_view`	view result by napari GUI, only available in single file mode (default: False)
`no_normalize`	not do percentile-based image normalization (default: False)
`save_ij_roi`	if save also the imageJ/Fiji compatible .roi file (default: False)
`with_norm`	flag normalize image

DESCRIPTION: str | None = 'Base Cellular Segmentation Option': parser description. Could be override as a method if its content is dynamic-generated.

GROUP_IO = 'Data I/O Options'

EX_GROUP_SOURCE = 'EX_GROUP_SOURCE'

file: Path: image file path

directory: Path: directory for batch imaging processing

directory_suffix: Literal['.tif', '.tiff', '.png']: suffix in the directory for batch mode (default: ‘.tif’)

save_ij_roi: bool: if save also the imageJ/Fiji compatible .roi file (default: False)

model: str: which pretrained model for evaluation

invalid_existed_result: bool: force re-evaluate the result (default: False)

no_normalize: bool: not do percentile-based image normalization (default: False)

napari_view: bool: view result by napari GUI, only available in single file mode (default: False)

property file_mode: bool: flag file mode

property batch_mode: bool: flag batch mode

property with_norm: bool: flag normalize image

process_image(to_gray=True)[source]

Process the image for segmentation.

Returns:: Array[Any, [H, W]] or Array[Any, [H, W, C]]
Parameters:: to_gray (bool)
Return type:: ndarray

foreach_process_image(to_gray=True)[source]

Iterates over image files in the specified directory, processes each image, and yields the file path along with the processed image. The processing can include grayscale conversion and normalization based on the provided parameters.

Parameters:: to_gray (bool) – Flag indicating whether the images should be converted to grayscale.
Returns:: An iterable of tuples where each tuple includes the file path as a Path object and the processed image as a numpy array.
Return type:: Tuple of filepath, image_array (Array[Any, [H, W]] or Array[Any, [H, W, C]]) generator

abstractmethod seg_output(filepath)[source]

Get segmented output save path

Parameters:: filepath (Path) – filepath for image
Returns:: segmented output save path
Return type:: Path

ij_roi_output(filepath)[source]

Get imageJ/Fiji .roi output save path

Parameters:: filepath (Path) – filepath for image
Returns:: ij roi output save path
Return type:: Path

abstractmethod eval()[source]

eval the model in single file or batch files in directory, and save the results

Return type:: None

abstractmethod launch_napari(**kwargs)[source]: run napari GUI viewer