CSemanticSegmentationIO

class ikomia.dataprocess.pydataprocess.CSemanticSegmentationIO

Define input or output managing common information extracted by semantic segmentation task. Such task are able to automatically set a class for each pixel of an image. Thus, this input/output stores labelled image, class names and class colors. Among others, algorithms like DeepLabV3+, UNet or TransUNet are semantic segmentation tasks.

Import

from ikomia.dataprocess import CSemanticSegmentationIO

Methods

__init__(arg1)	__init__( (object)self) -> None :
get_mask(self)	Get labelled image (ie graylevel) where each pixel has a specific value corresponding to its class.
get_class_names(self)	Get class names list associated with the semantic mask.
get_colors(self)	Get colors associated with class names.
get_polygons(self)	Get polygons of connected components extracted from segmentation mask.
set_class_colors(self, colors)	Set class colors associated with segmentation mask.
set_class_names(self, names)	Set class names associated with segmentation mask.
set_mask(self, mask)	Set the mask of the semantic segmentation output.

Overridden methods

clear_data(self)	See clear_data().
from_json(self, jsonStr)	Set input/output data from JSON formatted string.
is_data_available(self)	See is_data_available().
load(self, path)	Load instance segmentation input/output for JSON file.
save(self, path)	Save instance segmentation input/output to JSON file.
to_json(self)	Return input/output data in JSON formatted string (compact mode and image encoded as JPEG).

Inherited methods

copy_static_data(self, io)	Copy the static data from the given input or ouput.
get_unit_element_count(self)	Get the number of unit elements in terms of processing scheme.

Attributes

auto_save	Auto-save status
data_type	I/O data type
dim_count	Number of dimensions
description	Custom description to explain input/output type and use
displayable	Displayable status (Ikomia Studio)
name	I/O name
source_file_path	Path to the source file used as workflow input (if any)

Details

__init__((object)arg1) → None

__init__( (object)self) -> None :

Default constructor

__init__( (object)arg1, (CSemanticSegmentationIO)arg2) -> None :

Copy constructor

from_json((CSemanticSegmentationIO)self, (str)jsonStr) → None :

Set input/output data from JSON formatted string.

Args:

str: data as JSON formatted string

from_json( (CSemanticSegmentationIO)self, (str)jsonStr) -> None

get_mask((CSemanticSegmentationIO)self) → object :

Get labelled image (ie graylevel) where each pixel has a specific value corresponding to its class. You can find the correspondence between pixel value and class name with ikomia.dataprocess.pydataprocess.CSemanticIO.get_class_names().

Returns:

grayscale mask

Return type:

Numpy array

get_class_names((CSemanticSegmentationIO)self) → object :

Get class names list associated with the semantic mask. Class index in the list corresponds to the pixel value in the mask.

Returns:

class names

Return type:

list of str

get_colors((CSemanticSegmentationIO)self) → object :

Get colors associated with class names.

Returns:

colors as [r, g, b] list

Return type:

list of int list

get_polygons((CSemanticSegmentationIO)self) → object :

Get polygons of connected components extracted from segmentation mask.

Returns:

list of CGraphicsItem based objects

is_data_available((CSemanticSegmentationIO)self) → bool :

See is_data_available().

is_data_available( (CSemanticSegmentationIO)self) -> bool

load((CSemanticSegmentationIO)self, (str)path) → None :

Load instance segmentation input/output for JSON file.

Args:

path (str): path to JSON file

load( (CSemanticSegmentationIO)self, (str)path) -> None

save((CSemanticSegmentationIO)self, (str)path) → None :

Save instance segmentation input/output to JSON file.

Args:

path (str): path to JSON file

save( (CSemanticSegmentationIO)self, (str)path) -> None

set_class_names((CSemanticSegmentationIO)self, (object)names) → None :

Set class names associated with segmentation mask. If colors are not defined, random colors are automatically generated.

Parameters:

names (list of str) – class names, index in the list must match the pixel value in the mask

set_class_colors((CSemanticSegmentationIO)self, (object)colors) → None :

Set class colors associated with segmentation mask. Sizes of names and colors must be equal.

Parameters:

colors (list of list of int) – colors as [r, g, b] list

set_mask((CSemanticSegmentationIO)self, (object)mask) → None :

Set the mask of the semantic segmentation output.

Parameters:

mask (numpy array) – segmentation mask

to_json((CSemanticSegmentationIO)self) → str :

Return input/output data in JSON formatted string (compact mode and image encoded as JPEG).

Returns:

string: JSON formatted string

to_json( (CSemanticSegmentationIO)self) -> str

to_json( (CSemanticSegmentationIO)self, (object)options) -> str :

Return input/output data in JSON formatted string. JSON format options can be set, possible values are:

• [‘json_format’, ‘compact’] (default)

• [‘json_format’, ‘indented’]

• [‘image_format’, ‘jpg’](for the mask - default)

• [‘image_format’, ‘png’]

Args:

list of str: format-specific options encoded as pairs [option_name, option_value]

Returns:

string: JSON formatted string

to_json( (CSemanticSegmentationIO)self, (object)options) -> str