Class ReduceLogSum
Represents a ReduceLogSum reduction layer along the given axes: f(x1, x2 ... xn) = log(x1 + x2 + ... + xn).
Inherited Members
Namespace: Unity.Sentis.Layers
Syntax
[Serializable]
public class ReduceLogSum : ReduceConstructors
ReduceLogSum(String, String[], Boolean, Boolean)
Initializes and returns an instance of ReduceLogSum reduction layer.
Declaration
public ReduceLogSum(string name, string[] inputs, bool keepdims = true, bool noopWithEmptyAxes = false)Parameters
| Type | Name | Description |
|---|---|---|
| String | name | The name to use for the output tensor of the layer. |
| String[] | inputs | The name of the input tensor and optionally the axes tensor. If no axes tensor is provided, the layer performs the reduction according to the value of |
| Boolean | keepdims | Whether to keep the axis dimension in the output tensor. The default value is |
| Boolean | noopWithEmptyAxes | Whether to perform an identity operation if the input axes tensor is empty. The default value is |
Methods
Execute(Tensor[], ExecutionContext)
Executes the layer using the operations and variables from the ExecutionContext and returns the output tensor.
If the layer has more than one output, output tensors are saved to variables.
Declaration
public override Tensor Execute(Tensor[] inputTensors, ExecutionContext ctx)Parameters
| Type | Name | Description |
|---|---|---|
| Tensor[] | inputTensors | |
| ExecutionContext | ctx |
Returns
| Type | Description |
|---|---|
| Tensor |