View Autogenerated Custom Layers Using Deep Network Designer

This example shows how to import a pretrained TensorFlow™ network and view the autogenerated layers in Deep Network Designer.

Import a pretrained TensorFlow network in the saved model format as a DAGNetwork object. The imported network contains layers that are not supported for conversion into built-in MATLAB® layers. The software automatically generates custom layers when you import these layers.

Specify the model folder.

if ~exist("digitsDAGnetwithnoise","dir")
    unzip("digitsDAGnetwithnoise.zip")
end
modelFolder = "./digitsDAGnetwithnoise";

Specify the class names.

classNames = {'0','1','2','3','4','5','6','7','8','9'};

Import a TensorFlow™ network in the saved model format. By default, importTensorFlowNetwork imports the network as a DAGNetwork object. Specify the output layer type for an image classification problem.

net = importTensorFlowNetwork(modelFolder, ...
    OutputLayerType="classification", ...
    Classes=classNames);

Importing the saved model...
Translating the model, this may take a few minutes...
Finished translation. Assembling network...
Import finished.

View the network in Deep Network Designer.

deepNetworkDesigner(net)

If the imported network contains layers not supported for conversion into built-in MATLAB layers, then the importTensorFlowNetwork function can automatically generate custom layers in place of these layers. importTensorFlowNetwork saves each generated custom layer to a separate .m file in the package +digitsDAGnetwithnoise in the current folder.

The autogenerated layers appear in the Deep Network Designer canvas as gray icons with names starting with "k". Select a layer to see more information about its properties.

You can view and edit the layer code by clicking Edit Layer Code. The class file opens in the MATLAB® Editor.