Convolution 2D Layer
Libraries:
Deep Learning Toolbox /
Deep Learning Layers /
Convolution and Fully Connected Layers
Description
The Convolution 2D Layer block applies sliding convolutional filters to 2-D
input. The layer convolves the input by moving the filters along the input vertically and
horizontally and computing the dot product of the weights and the input, and then adding a
bias term. This block accepts 2-D image data in the SSC
format (three
dimensions corresponding to two spatial dimensions and one channel dimension, in that order)
and convolves over the spatial dimensions.
The exportNetworkToSimulink
function generates this block to represent a convolution2dLayer
object.
Limitations
The Layer parameter has limited support for the
'manual'
padding mode. It is recommended to use aconvolution2dLayer
object that has thePaddingMode
property set to'same'
.The Layer parameter does not support
convolution2dLayer
objects that have thePaddingValue
property set to"symmetric-exclude-edge"
. If you specify an object that uses that padding value, the block produces a warning and uses the value"symmetric-include-edge"
instead.The Layer parameter does not support
convolution2dLayer
objects that have theDilationFactor
property set to a value other than1
.
Ports
Input
Output
Parameters
Extended Capabilities
Version History
Introduced in R2024b