Interface IWorker

An interface that allows you to execute neural networks (models).

IWorker abstracts implementation details on different hardware devices such as the CPU and the GPU. IWorker lets you do the following:

• Specify inputs.
• Schedule the work.
• Get outputs.

Internally, IWorker translates the neural network from a Model into a set of operations, then sends the operations to the hardware device for asynchronous execution.

Use WorkerFactory.CreateWorker or Model.CreateWorker to create a new instance of a worker.

Inherited Members

IDisposable.Dispose()

Namespace: Unity.Sentis

Assembly: Unity.Sentis.dll

Syntax

public interface IWorker : IDisposable

Properties

scheduleProgress

Returns the proportion of the model scheduled for execution since the last call to ExecuteLayerByLayer.

Returns 0.0 after you call ExecuteLayerByLayer. Returns 1.0 when the model is fully scheduled.

The value increases each time you iterate on the IEnumerator that ExecuteLayerByLayer returns.

Declaration

float scheduleProgress { get; }

Property Value

Type	Description
float

Methods

Execute()

Schedules the execution of the model on the worker. This is non-blocking.

Declaration

IWorker Execute()

Returns

Type	Description
IWorker	The IWorker.

Execute(IDictionary<string, Tensor>)

Sets multiple tensors as the inputs of the model and schedules execution of the model. This is non-blocking.

Declaration

IWorker Execute(IDictionary<string, Tensor> inputTensors)

Parameters

Type	Name	Description
IDictionary<string, Tensor>	inputTensors	The tensors to use as the inputs of the model as a dictionary mapping input names to tensors.

Returns

Type	Description
IWorker	The IWorker.

Execute(Tensor)

Sets a tensor as the default input of the model and schedules the execution of the model on the worker. This is non-blocking. For models with more than one input this sets the first input.

Declaration

IWorker Execute(Tensor inputTensor)

Parameters

Type	Name	Description
Tensor	inputTensor	The tensor to set to the default input of the model.

Returns

Type	Description
IWorker	The IWorker.

ExecuteLayerByLayer()

Schedules the execution of the model one layer at a time. This is non-blocking.

To schedule the execution of the next layer of the model, call MoveNext on the IEnumerator object this method returns.

Declaration

IEnumerator ExecuteLayerByLayer()

Returns

Type	Description
IEnumerator	The IEnumerator for scheduling manual execution.

ExecuteLayerByLayer(IDictionary<string, Tensor>)

Sets multiple tensors as the inputs of the model and schedules execution of the model one layer at a time. This is non-blocking.

To schedule execution of the next layer of the model, call MoveNext on the IEnumerator object this method returns.

Declaration

IEnumerator ExecuteLayerByLayer(IDictionary<string, Tensor> inputTensors)

Parameters

Type	Name	Description
IDictionary<string, Tensor>	inputTensors	The tensors to use as the inputs of the model as a dictionary mapping input names to tensors.

Returns

Type	Description
IEnumerator	The IEnumerator for scheduling manual execution.

ExecuteLayerByLayer(Tensor)

Sets a tensor as the default input of the model and schedules execution of the model one layer at a time. This is non-blocking. For models with more than one input this sets the first input.

To schedule execution of the next layer of the model, call MoveNext on the IEnumerator object this method returns.

Declaration

IEnumerator ExecuteLayerByLayer(Tensor inputTensor)

Parameters

Type	Name	Description
Tensor	inputTensor	The tensor to set to the default input of the model.

Returns

Type	Description
IEnumerator	The IEnumerator for scheduling manual execution.

GetBackend()

Returns the backend used for execution.

Declaration

IBackend GetBackend()

Returns

Type	Description
IBackend	The IBackend used.

PeekOutput()

Returns a reference to the default output tensor. This is non-blocking.

For models with more than one output this returns a reference to the first output tensor.

The reference is valid only until you call Execute() or Dispose() on the worker.

Declaration

Tensor PeekOutput()

Returns

Type	Description
Tensor	The output tensor reference.

PeekOutput(string)

Returns a reference to the default output tensor. This is non-blocking.

For models with more than one output this returns a reference to the first output tensor.

The reference is valid only until you call Execute() or Dispose() on the worker.

Declaration

Tensor PeekOutput(string name)

Parameters

Type	Name	Description
string	name	The name of the output tensor to peek.

Returns

Type	Description
Tensor	The output tensor reference.

SetInput(string, Tensor)

Sets a tensor as a named input of the model.

Declaration

void SetInput(string name, Tensor inputTensor)

Parameters

Type	Name	Description
string	name	The name of the input to set.
Tensor	inputTensor	The tensor to set as the input.

TakeOutputOwnership()

Takes ownership of the default output tensor. This is non-blocking.

For models with more than one output this returns a reference to the first output tensor.

Declaration

Tensor TakeOutputOwnership()

Returns

Type	Description
Tensor	The output tensor.

TakeOutputOwnership(string)

Takes ownership of an output tensor with a given name. This is non-blocking.

Declaration

Tensor TakeOutputOwnership(string name)

Parameters

Type	Name	Description
string	name	The name of the output tensor to take ownership of.

Returns

Type	Description
Tensor	The output tensor.