Creating the second convolution layer

In this recipe, let's create the second convolution layer.

Getting ready

The following are the inputs to the function create_conv_layer defined in the recipe Using functions to create a new convolution layer.

• Input: This is the four-dimensional output of the first convoluted layer; that is, layer_conv1
• Num_input_channels: This is the number of filters (or depth) in the first convoluted layer, num_filters1
• Filter_size: This is the height and width of the filter layer; namely, filter_size2
• Num_filters: This is the depth of the filter layer, num_filters2
• Use_pooling: This is the binary flag set to TRUE

How to do it...

1. Run the create_conv_layer function with the preceding input parameters:

# Convolutional Layer 2
conv2 <- create_conv_layer(input=layer_conv1,
num_input_channels=num_filters1,
filter_size=filter_size2,
num_filters=num_filters2,
use_pooling=TRUE)

2. Extract the layers of the second convolution layer:

layer_conv2 <- conv2$layer
conv2_images <- conv2...