monailabel.transform.post module

class monailabel.transform.post.BoundingBoxd(keys, result='result', bbox='bbox')[source]

Bases: monai.transforms.transform.MapTransform

class monailabel.transform.post.DumpImagePrediction2Dd(image_path, pred_path, pred_only=True)[source]

Bases: monai.transforms.transform.Transform

class monailabel.transform.post.ExtremePointsd(keys, result='result', points='points')[source]

Bases: monai.transforms.transform.MapTransform

class monailabel.transform.post.FindContoursd(keys, min_positive=10, min_poly_area=80, max_poly_area=0, result='result', result_output_key='annotation', key_label_colors='label_colors', key_foreground_points=None, labels=None, colormap=None)[source]

Bases: monai.transforms.transform.MapTransform

class monailabel.transform.post.LargestCCd(keys, has_channel=True)[source]

Bases: monai.transforms.transform.MapTransform

static get_largest_cc(label)[source]
class monailabel.transform.post.MergeAllPreds(keys, allow_missing_keys=False)[source]

Bases: monai.transforms.transform.MapTransform

Merge all predictions to one channel

Parameters

keys (Union[Collection[Hashable], Hashable]) – The keys parameter will be used to get and set the actual data item to transform

__init__(keys, allow_missing_keys=False)[source]

Merge all predictions to one channel

Parameters

keys (Union[Collection[Hashable], Hashable]) – The keys parameter will be used to get and set the actual data item to transform

class monailabel.transform.post.RenameKeyd(source_key, target_key)[source]

Bases: monai.transforms.transform.Transform

class monailabel.transform.post.Restored(keys, ref_image, has_channel=True, invert_orient=False, mode=InterpolateMode.NEAREST, config_labels=None, align_corners=None, meta_key_postfix='meta_dict')[source]

Bases: monai.transforms.transform.MapTransform