Conv2D Properties

The Conv2D type exposes the following members.

Properties


  Name Description
Public property Act
Activation function to use. If you don't specify anything, no activation is applied (ie. "linear" activation: a(x) = x). OptActivations
Public property BiasInitializer
Initializer for the bias vector. OptInitializers
Public property Channels
Gets or sets the channels.Integer, the dimensionality of the output space.
Public property Dialation
A tuple of 2 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any dilation_rate value != 1 is incompatible with specifying any stride value != 1.
Public property KernalSize
A tuple of 2 integers, specifying the width and height of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions.
Public property Name
Gets or sets the name of the network layer
(Inherited from LayerConfig.)
Public property Padding
Boolean, if true results in padding the input such that the output has the same length as the original input.
Public property Params
Gets or sets the parameters.
(Inherited from LayerConfig.)
Public property Shape
The 2D input shape
Public property Strides
A tuple of 2 integers, specifying the strides of the convolution along the width and height. Can be a single integer to specify the same value for all spatial dimensions. Specifying any stride value != 1 is incompatible with specifying any dilation_rate value != 1.
Public property UseBias
Boolean, whether the layer uses a bias vector.
Public property WeightInitializer
Initializer for the kernel weights matrix. OptInitializers