conv2D

Creates a convolutional layer typically found in a convnet used for image classification.

Layer
conv2D

Parameters

input
Type: Layer

The previous (i.e., input) layer.

outputChannels
Type: size_t

The number of feature maps that this layer should produce.

filterDims
Type: size_t[]

The size of the kernels that should be convolved with the inputs.

opts

Additional options, with sensible defaults.

Return Value

Type: Layer

The new convolutional Layer.

Meta