Model visualization

For simpler models, a simple model summary is sufficient, but for more complex topologies, Keras provides a way to visualize the model. It is a layer on top of the graphviz library.

Getting ready

Please make sure graphviz is installed:

sudo apt-get install graphviz

Also, install pydot, which is needed in the underlying implementation:

sudo pip install pydot

How to do it...

Let's take a look at an example where we create a simple model and call plot_model on it.

The plot_model() function in Keras creates a plot of the neural network. This function takes the following arguments:

• model: (required) The model that is to be plotted
• to_file: (required) The name of the file to save the plot
• show_shapes: (optional, defaults to False) Boolean to show the output shapes of each layer
• show_layer_names: (optional, defaults to True) Boolean to show the name for each layer

The following sections show how plot_model can be used.

Code listing

The following code creates a Sequential model with two Dense...