Method inference_step

official/core/base_task.py:311–323

Performs the forward step. With distribution strategies, this method runs on devices. Args: inputs: a dictionary of input tensors. model: the keras.Model. Returns: Model outputs.

(self, inputs, model: tf_keras.Model)

    return logs

  def inference_step(self, inputs, model: tf_keras.Model):
    """Performs the forward step.

    With distribution strategies, this method runs on devices.

    Args:
      inputs: a dictionary of input tensors.
      model: the keras.Model.

    Returns:
      Model outputs.
    """
    return model(inputs, training=False)

  def aggregate_logs(self, state, step_logs):
    """Optional aggregation over logs returned from a validation step.