AttributeModelOutput

class savant.base.model.AttributeModelOutput(layer_names=<factory>, converter=None, attributes='???')

AttributeModel output configuration template.

Validates entries in a module config file under model.output.

Example:

model:
    # model configuration
    output:
        layer_names: [output]
        attributes:
            - name: cat_or_dog
              threshold: 0.5

converter: PyFunc | None = None

Model output converter. Converter is used to transform raw tensor output into Savant data format.

Converter implementation should be written as a subclass of BaseObjectModelOutputConverter or BaseAttributeModelOutputConverter or BaseComplexModelOutputConverter depending on the model type.

layer_names: List[str]: Specify model output layer names.

attributes: List[AttributeModelOutputAttribute] = '???': Configuration for each output attribute of an attribute model.