TensorFlowLesson 21Free preview

TFJS Models

This lesson is part of A.I. · All levels

Summary

In TensorFlow.js, the model is usually made with tf.sequential() in the form of a layer stack, e.g. tf.layers.dense. Once the network structure is compiled, the model is compiled with the optimizer and loss function, and then trained with model.fit(). After the training is completed, model.predict() is used to predict new data.

Key points

Tf.sequential() make the model of stacks of layers one by one.
It adds a layer of dense neurons.
Model.compile() determines the optimizer and the loss function.
Model.fit() runs training with a certain data and epoch number.
Model.predict() is used to predict new data.

Full lesson

Code examples and quizzes

Full lessons, code examples, and quizzes are available to subscribers. 5 questions.