When function call() is called in the custom training?

I follow this guide for KD Knowledge Distillation and the source as

class Distiller(keras.Model):
    def __init__(self, student, teacher):
        super().__init__()
        self.teacher = teacher
        self.student = student

    def compile(
        self,
        optimizer,
        metrics,
        student_loss_fn,
        distillation_loss_fn,
        alpha=0.1,
        temperature=3,
    ):
        """Configure the distiller.

        Args:
            optimizer: Keras optimizer for the student weights
            metrics: Keras metrics for evaluation
            student_loss_fn: Loss function of difference between student
                predictions and ground-truth
            distillation_loss_fn: Loss function of difference between soft
                student predictions and soft teacher predictions
            alpha: weight to student_loss_fn and 1-alpha to distillation_loss_fn
            temperature: Temperature for softening probability distributions.
                Larger temperature gives softer distributions.
        """
        super().compile(optimizer=optimizer, metrics=metrics)
        self.student_loss_fn = student_loss_fn
        self.distillation_loss_fn = distillation_loss_fn
        self.alpha = alpha
        self.temperature = temperature

    def compute_loss(
        self, x=None, y=None, y_pred=None, sample_weight=None, allow_empty=False
    ):
        teacher_pred = self.teacher(x, training=False)
        student_loss = self.student_loss_fn(y, y_pred)

        distillation_loss = self.distillation_loss_fn(
            ops.softmax(teacher_pred / self.temperature, axis=1),
            ops.softmax(y_pred / self.temperature, axis=1),
        ) * (self.temperature**2)

        loss = self.alpha * student_loss + (1 - self.alpha) * distillation_loss
        return loss

    def call(self, x):
        return self.student(x)

When training, at each epoch does the customized function call() is called?

Or it is only called when we call evaluate() or predict() after training?
Thank you.

Hi @DEV_AI, thanks for posting this issue.

The call() method is invoked during training, evaluation, and prediction, when the model is run with inputs or every time data flows through the model call() will be executed.