The following are the inputs to the function defined in the recipe Using functions to flatten the densely connected layer, create_fc_layer:

• Input: This is the flattened convolution layer; that is, layer_flat
• Num_inputs: This is the number of features created post flattening, num_features
• Num_outputs: This is the number of fully connected neurons output, fc_size
• Use_relu: This is the binary flag set to TRUE to incorporate non-linearity in the tensor