Hands-On Machine Learning with TensorFlow.js

Model summary

Inspecting the structure of the model is often helpful if we wish to debug models and ensure they're constructed correctly. The summary() method is a tool that we can use to print information about the model's structure, such as the following:

• The name and type of each layer
• The output shape of each layer
• The number of weight parameters in each layer
• The total number of trainable and non-trainable parameters

For example, the model that we created previously, which had one intermediate layer, provides the following summary information:

The structure of the model has a significant impact on its accuracy and performance, so we ...