Class Conv

Represents a Conv convolution layer, which applies a convolution filter to an input tensor.

Inheritance
Object
Layer
FusedActivation
Conv
Inherited Members
Namespace: Unity.Sentis.Layers
Syntax
[Serializable]
public class Conv : FusedActivation

Constructors

Conv(String, String, String, String, Int32, Int32[], Int32[], Int32[], AutoPad, Int32[], FusableActivation)

Initializes and returns an instance of Conv convolution layer.

Declaration
public Conv(string name, string X, string W, string B, int group, int[] strides, int[] pads, int[] dilations, AutoPad autoPad = AutoPad.NotSet, int[] kernelShape = null, FusableActivation fusedActivation = FusableActivation.None)
Parameters
Type Name Description
String name

The name to use for the output tensor of the layer.
String X

The name to use for the input tensor of the layer.
String W

The name to use for the filter tensor of the layer.
String B

The name to use for the optional bias tensor of the layer.
Int32 group

The number of groups that input channels and output channels are divided into.
Int32[] strides

The optional stride value for each spatial dimension of the filter.
Int32[] pads

The optional lower and upper padding values for each spatial dimension of the filter.
Int32[] dilations

The optional dilation value of each spatial dimension of the filter.
AutoPad autoPad

The auto padding mode of the convolution as an AutoPad.
Int32[] kernelShape
FusableActivation fusedActivation

The fused activation type to apply after the convolution. The default value is None.

Fields

autoPad

The auto padding mode of the convolution as an AutoPad.

Declaration
public AutoPad autoPad
Field Value
Type Description
AutoPad

dilations

The dilation value of each spatial dimension of the filter.

If this is null the layer uses a default of [1, 1, ..., 1].

Declaration
public int[] dilations
Field Value
Type Description
Int32[]

group

The number of groups that input channels and output channels are divided into.

Declaration
public int group
Field Value
Type Description
Int32

kernelShape

Declaration
public int[] kernelShape
Field Value
Type Description
Int32[]

pads

The lower and upper padding values for each spatial dimension of the filter, [pad_left, pad_right] for 1D, [pad_top, pad_bottom, pad_left, pad_right] for 2D, etc.

If this is null the layer uses a default of [0, 0, ..., 0].

Declaration
public int[] pads
Field Value
Type Description
Int32[]

strides

The stride value for each spatial dimension of the filter.

If this is null the layer uses a default of [1, 1, ..., 1].

Declaration
public int[] strides
Field Value
Type Description
Int32[]

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
Overrides

ToString()

Returns a string that represents the Layer.

Declaration
public override string ToString()
Returns
Type Description
String
Overrides