Class GenericWorker

Generic IWorker implementation

Inheritance
Object
GenericWorker
Namespace: Unity.Barracuda
Syntax
public class GenericWorker : object, IWorker, IDisposable

Constructors

GenericWorker(Model, IOps, IVars, Boolean)

Create GenericWorker for specified model and ops

Declaration
public GenericWorker(Model model, IOps ops, IVars vars, bool verbose = false)
Parameters
Type Name Description
Model model

Model
IOps ops

IOps
IVars vars

IVars
Boolean verbose

verbose execution flag

Properties

scheduleProgress

Reports the fraction (from 0.0 to 1.0) of the model that was scheduled for the execution since the last call to StartManualSchedule. This property will return 0.0 immediately after calling StartManualSchedule and will return 1.0 once the complete model was scheduled. This property will monotonuosly increase with the every iteration of IEnumerator that was obtained by calling StartManualSchedule.

Declaration
public virtual float scheduleProgress { get; }
Property Value
Type Description
Single
Implements

Methods

Dispose()

Dispose all internal storage structures

Declaration
public virtual void Dispose()

Execute()

Non-blocking API that schedules network execution in one go.

Declaration
public virtual IWorker Execute()
Returns
Type Description
IWorker

IWorker instance
Implements

Execute(IDictionary<String, Tensor>)

Non-blocking API that takes multiple input tensors and schedules network execution in one go.

Declaration
public virtual IWorker Execute(IDictionary<string, Tensor> inputs)
Parameters
Type Name Description
IDictionary<String, Tensor> inputs

input Tensor Dictionary: name -> Tensor
Returns
Type Description
IWorker

IWorker instance
Implements

Execute(Tensor)

Non-blocking API that takes single input tensor and schedules network execution in one go. Useful when network have only one input as input name is not needed.

Declaration
public virtual IWorker Execute(Tensor input)
Parameters
Type Name Description
Tensor input

input Tensor
Returns
Type Description
IWorker

IWorker instance
Implements

Finalize()

Finalizer

Declaration
protected void Finalize()

FlushSchedule(Boolean)

Non-blocking API that starts immediate execution on the part of the network that was scheduled so far. Optional blocking flag can force this function to block until execution is complete.

Declaration
public virtual void FlushSchedule(bool blocking)
Parameters
Type Name Description
Boolean blocking

if blocking True, wait for completion
Implements

PeekConstants(String)

Returns references to constants tensors for a layer. This reference might be valid only until the next Execute() or Dispose() method is called on the worker. IMPORTANT: if you want tensor to outlive the worker, use CopyOutput() method or follow with TakeOwnership() call on the tensor, also worker Execute() or PrepareForInput() should have been called at least once for the tensors to exist.

Declaration
public virtual Tensor[] PeekConstants(string layerName)
Parameters
Type Name Description
String layerName

Layer name
Returns
Type Description
Tensor[]

array of constant Tensors
Implements

PeekOutput()

Non-blocking API that returns a reference to the main output tensor. This reference will be valid only until the next Execute() or Dispose() method is called on the worker. Useful when network has only one output. IMPORTANT: if you want tensor to outlive the worker, use CopyOutput() method or follow with TakeOwnership() call on the tensor.

Declaration
public virtual Tensor PeekOutput()
Returns
Type Description
Tensor

output Tensor
Implements

PeekOutput(String)

Non-blocking API that returns a reference to output tensor by specified name. This reference will be valid only until the next Execute() or Dispose() method is called on the worker. IMPORTANT: if you want tensor to outlive the worker, use CopyOutput() method or follow with TakeOwnership() call on the tensor.

Declaration
public virtual Tensor PeekOutput(string name)
Parameters
Type Name Description
String name

output name
Returns
Type Description
Tensor

output Tensor
Implements

PrepareForInput(IDictionary<String, TensorShape>)

Optional API to prepare network execution for inputs of particular shapes. Useful to initialize execution device ahead of the first call to Execute.

Declaration
public virtual void PrepareForInput(IDictionary<string, TensorShape> inputShapes)
Parameters
Type Name Description
IDictionary<String, TensorShape> inputShapes

Dictionary of tensor name -> input shapes
Implements

SetInput(String, Tensor)

Assign tensor x to the named input of the network. String name specifies the name of the input.

Declaration
public virtual void SetInput(string name, Tensor x)
Parameters
Type Name Description
String name

Tensor name
Tensor x

Tensor
Implements

SetInput(Tensor)

Specify single tensor x as the only input for the network. Useful when network has only one input and caller does not need to specify input's name.

Declaration
public virtual void SetInput(Tensor x)
Parameters
Type Name Description
Tensor x

input Tensor
Implements

StartManualSchedule()

Non-blocking API that allows manual scheduling of the model one layer at the time. Call MoveNext on the IEnumerator obtained from calling this function to schedule next layer of the model.

Declaration
public virtual IEnumerator StartManualSchedule()
Returns
Type Description
IEnumerator

Manual schedule iterator
Implements

StartManualSchedule(IDictionary<String, Tensor>)

Non-blocking API that takes mutliple input tensors and schedules network execution one layer at the time. Call MoveNext on the IEnumerator obtained from calling this function to schedule next layer of the model.

Declaration
public virtual IEnumerator StartManualSchedule(IDictionary<string, Tensor> inputs)
Parameters
Type Name Description
IDictionary<String, Tensor> inputs

input Tensor Dictionary: name -> Tensor
Returns
Type Description
IEnumerator

Manual schedule iterator
Implements

StartManualSchedule(Tensor)

Non-blocking API that takes single input tensor and schedules network execution one layer at the time. Call MoveNext on the IEnumerator obtained from calling this function to schedule next layer of the model.

Declaration
public virtual IEnumerator StartManualSchedule(Tensor input)
Parameters
Type Name Description
Tensor input

input Tensor
Returns
Type Description
IEnumerator

Manual schedule iterator
Implements

Summary()

Execution summary

Declaration
public virtual string Summary()
Returns
Type Description
String

execution summary
Implements