monai.deploy.operators.InferenceOperator¶

class monai.deploy.operators.InferenceOperator(fragment, *args, **kwargs)[source]¶

Bases: holoscan.core.Operator

The base operator for operators that perform AI inference.

This operator performs pre-transforms on a input image, inference with a given model, post-transforms, and final results generation.

Constructor of the operator.

Methods

`__init__`(fragment, args, *kwargs)	Constructor of the operator.
`add_arg`(args, *kwargs)	Overloaded function.
`compute`(op_input, op_output, context)	An abstract method that needs to be implemented by the user.
`initialize`()	Default implementation of initialize
`post_process`(data, args, *kwargs)	Transform the prediction results from the model(s).
`pre_process`(data, args, *kwargs)	Transforms input before being used for predicting on a model.
`predict`(data, args, *kwargs)	Predicts results using the models(s) with input tensors.
`resource`(self, name)	Resources associated with the operator.
`setup`(spec)	Default implementation of setup method.
`start`()	Default implementation of start
`stop`()	Default implementation of stop

Attributes

`args`	The list of arguments associated with the component.
`conditions`	Conditions associated with the operator.
`description`	YAML formatted string describing the operator.
`fragment`	The fragment (`holoscan.core.Fragment`) that the operator belongs to.
`id`	The identifier of the component.
`is_metadata_enabled`	Boolean indicating whether the fragment this operator belongs to has metadata transmission enabled.
`metadata`	The metadata dictionary (`holoscan.core.MetadataDictionary`) associated with the operator.
`metadata_policy`	The metadata dictionary (`holoscan.core.MetadataPolicy`) associated with the operator.
`name`	The name of the operator.
`operator_type`	The operator type.
`resources`	Resources associated with the operator.
`spec`	The operator spec (`holoscan.core.OperatorSpec`) associated with the operator.

class OperatorType(self: holoscan.core._core.Operator.OperatorType, value: int) → None¶

Bases: pybind11_builtins.pybind11_object

Enum class for operator types used by the executor.

NATIVE: Native operator.
GXF: GXF operator.
VIRTUAL: Virtual operator. (for internal use, not intended for use by application authors)

Members:

NATIVE

GXF

VIRTUAL

property name¶

__init__(fragment, *args, **kwargs)[source]¶: Constructor of the operator.

add_arg(*args, **kwargs)¶

Overloaded function.

add_arg(self: holoscan.core._core.Operator, arg: holoscan.core._core.Arg) -> None

Add an argument to the component.

add_arg(self: holoscan.core._core.Operator, arg: holoscan.core._core.ArgList) -> None

Add a list of arguments to the component.

add_arg(self: holoscan.core._core.Operator, **kwargs) -> None

Add arguments to the component via Python kwargs.

add_arg(self: holoscan.core._core.Operator, arg: holoscan.core._core.Condition) -> None
add_arg(self: holoscan.core._core.Operator, arg: holoscan.core._core.Resource) -> None

Add a condition or resource to the Operator.

This can be used to add a condition or resource to an operator after it has already been constructed.

argholoscan.core.Condition or holoscan.core.Resource: The condition or resource to add.

property args¶

The list of arguments associated with the component.

arglist : holoscan.core.ArgList

compute(op_input, op_output, context)[source]¶

An abstract method that needs to be implemented by the user.

Parameters

op_input (InputContext) – An input context for the operator.
op_output (OutputContext) – An output context for the operator.
context (ExecutionContext) – An execution context for the operator.

property conditions¶: Conditions associated with the operator.

property description¶: YAML formatted string describing the operator.

property fragment¶: The fragment (holoscan.core.Fragment) that the operator belongs to.

property id¶

The identifier of the component.

The identifier is initially set to -1, and will become a valid value when the component is initialized.

With the default executor (holoscan.gxf.GXFExecutor), the identifier is set to the GXF component ID.

id : int

initialize()¶: Default implementation of initialize

property is_metadata_enabled¶: Boolean indicating whether the fragment this operator belongs to has metadata transmission enabled.

property metadata¶: The metadata dictionary (holoscan.core.MetadataDictionary) associated with the operator.

property metadata_policy¶: The metadata dictionary (holoscan.core.MetadataPolicy) associated with the operator.

property name¶: The name of the operator.

property operator_type¶

The operator type.

holoscan.core.Operator.OperatorType enum representing the type of the operator. The two types currently implemented are native and GXF.

post_process(data, *args, **kwargs)[source]¶

Transform the prediction results from the model(s).

This method must be overridden by a derived class.

Raises: NotImplementedError – When the subclass does not override this method.
Return type: Union[Image, Any, Tuple[Any, …], Dict[Any, Any]]

pre_process(data, *args, **kwargs)[source]¶

Transforms input before being used for predicting on a model.

This method must be overridden by a derived class.

Raises: NotImplementedError – When the subclass does not override this method.
Return type: Union[Image, Any, Tuple[Any, …], Dict[Any, Any]]

predict(data, *args, **kwargs)[source]¶

Predicts results using the models(s) with input tensors.

This method must be overridden by a derived class.

Raises: NotImplementedError – When the subclass does not override this method.
Return type: Union[Image, Any, Tuple[Any, …], Dict[Any, Any]]

resource(self: holoscan.core._core.Operator, name: str) → Optional[object]¶

Resources associated with the operator.

name : str The name of the resource to retrieve

holoscan.core.Resource or None: The resource with the given name. If no resource with the given name is found, None is returned.

property resources¶: Resources associated with the operator.

setup(spec)¶: Default implementation of setup method.

property spec¶: The operator spec (holoscan.core.OperatorSpec) associated with the operator.

start()¶: Default implementation of start

stop()¶: Default implementation of stop

monai.deploy.operators.EquipmentInfo monai.deploy.operators.IOMapping