Class GenericWorker

Represents a generic implementation of an IWorker.

Inheritance
Object
GenericWorker
Inherited Members
Namespace: Unity.Sentis
Syntax
public class GenericWorker : IWorker, IDisposable

Constructors

GenericWorker(Model, IOps, IVars, Boolean, Boolean)

Initializes and returns an instance of GenericWorker for the specified model and ops.

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

Properties

scheduleProgress

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

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

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

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

Methods

Dispose()

Disposes of the worker and any associated memory.

Declaration
public virtual void Dispose()
Implements

Execute()

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

Declaration
public virtual IWorker Execute()
Returns
Type Description
IWorker
Implements

Execute(IDictionary<String, Tensor>)

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

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

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

Finalize()

Finalizes the GenericWorker.

Declaration
protected void Finalize()

FlushSchedule(Boolean)

Schedules the execution of the part of the model that hasn't been scheduled yet. This is non-blocking.

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

When the value is true, the method blocks further code until the model finishes executing.
Implements

GetOps()

Declaration
public IOps GetOps()
Returns
Type Description
IOps
Implements

PeekOutput(Boolean)

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.

If you want to dispose of the worker but keep the tensor, use CopyOutput() instead, or use TakeOwnership() on the output tensor.

Declaration
public virtual Tensor PeekOutput(bool prepareCacheForAccess = false)
Parameters
Type Name Description
Boolean prepareCacheForAccess

Schedules a non-blocking download from the GPU to the CPU.
Returns
Type Description
Tensor
Implements

PeekOutput(String, Boolean)

Returns a reference to an output tensor with a given name. This is non-blocking.

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

If you want to dispose of the worker but keep the tensor, use CopyOutput() instead, or use TakeOwnership() on the output tensor.

Declaration
public virtual Tensor PeekOutput(string name, bool prepareCacheForAccess = false)
Parameters
Type Name Description
String name

The name of the output tensor to peek.
Boolean prepareCacheForAccess

Whether to schedule a non-blocking download to the CPU.
Returns
Type Description
Tensor
Implements

PrepareForInput(IDictionary<String, TensorShape>)

Prepares the worker to execute the model using inputs of given shapes.

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

A dictionary mapping input names to tensor shapes.
Implements

SetInput(String, Tensor)

Sets a tensor as a named input of the model.

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

The name of the input to set.
Tensor x
Implements

SetInput(Tensor)

Sets a tensor as the default input of the model. For models with more than one input this sets the first input.

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

StartManualSchedule()

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
public virtual IEnumerator StartManualSchedule()
Returns
Type Description
IEnumerator
Implements

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

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

Summary()

Returns a summary of the execution as a string.

Declaration
public virtual string Summary()
Returns
Type Description
String
Implements

Extension Methods