Class FunctionalGraph

Represents a model graph using the functional API.

Input functional tensors can be added to the graph, then manipulated using the functional API methods.

The functional graph can be compiled to return an optimized Inference Engine runtime model.

Inheritance

object

FunctionalGraph

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Namespace: Unity.InferenceEngine

Assembly: Unity.InferenceEngine.dll

Syntax

[MovedFrom("Unity.Sentis")]
public class FunctionalGraph

Methods

AddInput(DataType, DynamicTensorShape, string)

Append an input to the graph with an input def.

Declaration

public FunctionalTensor AddInput(DataType dataType, DynamicTensorShape shape, string name = null)

Parameters

Type	Name	Description
DataType	dataType	The data type of the input.
DynamicTensorShape	shape	The shape of the input.
string	name	The name of the input.

Returns

Type	Description
FunctionalTensor	The functional tensor input.

AddInput(DataType, TensorShape, string)

Append an input to the graph with an input def.

Declaration

public FunctionalTensor AddInput(DataType dataType, TensorShape shape, string name = null)

Parameters

Type	Name	Description
DataType	dataType	The data type of the input.
TensorShape	shape	The shape of the input.
string	name	The name of the input.

Returns

Type	Description
FunctionalTensor	The functional tensor input.

AddInput(Model, int, string)

Append an input to the graph matching a model input.

Declaration

public FunctionalTensor AddInput(Model model, int index, string name = null)

Parameters

Type	Name	Description
Model	model	The model.
int	index	The input index of the input in the provided model.
string	name	Name to use for this input. If name is null Inference Engine uses the name from the model.

Returns

Type	Description
FunctionalTensor	The functional tensor input.

AddInput<T>(DynamicTensorShape, string)

Append an input to the graph with a type T and dynamic tensor shape.

Declaration

public FunctionalTensor AddInput<T>(DynamicTensorShape shape, string name = null) where T : unmanaged

Parameters

Type	Name	Description
DynamicTensorShape	shape	The shape of the input.
string	name	The name of the input.

Returns

Type	Description
FunctionalTensor	The functional tensor input.

Type Parameters

Name	Description
T	The data type of the input.

AddInput<T>(TensorShape, string)

Append an input to the graph with a type T and static tensor shape.

Declaration

public FunctionalTensor AddInput<T>(TensorShape shape, string name = null) where T : unmanaged

Parameters

Type	Name	Description
TensorShape	shape	The shape of the input.
string	name	The name of the input.

Returns

Type	Description
FunctionalTensor	The functional tensor input.

Type Parameters

Name	Description
T	The data type of the input.

AddInputs(Model)

Append inputs to the graph matching all of a model's input.

Declaration

public FunctionalTensor[] AddInputs(Model model)

Parameters

Type	Name	Description
Model	model	The model.

Returns

Type	Description
FunctionalTensor[]	The functional tensor input array.

AddOutput(FunctionalTensor, string)

Append an output to the graph from a functional tensor.

Declaration

public void AddOutput(FunctionalTensor output, string name = null)

Parameters

Type	Name	Description
FunctionalTensor	output	The output functional tensor.
string	name	The name for the output. If null the name will be "output_{idx}" or inferred from the original model in case this functional tensor is the output of a forward pass of an existing model.

AddOutputs(params FunctionalTensor[])

Append outputs to the graph from multiple functional tensors.

Declaration

public void AddOutputs(params FunctionalTensor[] outputs)

Parameters

Type	Name	Description
FunctionalTensor[]	outputs	The output functional tensors.

Compile()

Compile and return an optimized runtime model.

Declaration

public Model Compile()

Returns

Type	Description
Model	The compiled runtime model.

Compile(params FunctionalTensor[])

Compile and return an optimized runtime model with given outputs.

Declaration

public Model Compile(params FunctionalTensor[] outputs)

Parameters

Type	Name	Description
FunctionalTensor[]	outputs	The outputs.

Returns

Type	Description
Model	The compiled runtime model.