fiftyone.utils.torch.SemanticSegmenterOutputProcessor

class documentation

class SemanticSegmenterOutputProcessor(OutputProcessor): (source)

Constructor: SemanticSegmenterOutputProcessor(classes)

View In Hierarchy

Output processor for semantic segementers.

Parameters
classesthe list of class labels for the model. This parameter is not used
Method __call__ Parses the model output.
Method __init__ Undocumented
Instance Variable classes Undocumented
def __call__(self, output, *args, **kwargs): (source)
overrides fiftyone.utils.torch.OutputProcessor.__call__

Parses the model output.

Parameters
output

a batch of predictions output = Dict[Tensor], where the dict has the following keys:

  • out (FloatTensor[N, M, H, W]): the segmentation map probabilities for the N images across the M classes
*argsunused arguments
**kwargsunused keyword arguments
Returns
a list of fiftyone.core.labels.Segmentation instances
def __init__(self, classes=None): (source)
overrides fiftyone.utils.torch.OutputProcessor.__init__

Undocumented

classes: None = (source)
overrides fiftyone.utils.torch.OutputProcessor.classes

Undocumented