DepthwiseConv2D

Description

Defines the weights of the DepthwiseConv2D layer selected by the name. Type : polymorphic.

Input parameters

 Model in : model architecture.
 name : string, name of layer.
 filters_depthwise : array, 4D values. filters_depthwise = [channels, 1, size[0], size[1]].
 biases : array, 1D values. biases = [channels].

Output parameters

 Model in : model architecture.

Dimension

• filters_depthwise = [channels, 1, size[0], size[1]]

The size of filters_depthwise depends on the input of the DepthwiseConv2D layer and the parameters size.
For example if the input of the layer has a size of [batch_size = 10, channels = 8, rows = 5, cols = 5] and size the value [3, 3] then filters will have a size of [channels = 8, 1, size[0] = 3, size[1] = 3].

• biases = [channels]

The size of biases depends on the parameter size of the DepthwiseConv2D layer.
For example, if the input of the layer has a size of [batch_size = 10, channels = 8, rows = 5, cols = 5] then biases will have a size of [channels = 8].

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install Deep Learning library to run it).