In this recipe, let's flatten the second convolution layer that we created.
The following is the input to the function defined in the recipe Creating the second convolution layer, flatten_conv_layer
:
Layer
: This is the output of the second convolution layer,layer_conv2
- Run the
flatten_conv_layer
function with the preceding input parameter:
flatten_lay <- flatten_conv_layer(layer_conv2)
- Extract the flattened layer:
layer_flat <- flatten_lay$layer_flat
- Extract the number of (input) features generated for each image:
num_features <- flatten_lay$num_features
Prior to connecting the output of the (second) convolution layer with a fully connected network, in step 1, we reshape the four-dimensional convolution layer into a two-dimensional tensor. The first dimension (?) represents any number of input images (as rows) and the second dimension represents the flattened vector of features generated for each image of...