Fix

               learning_rate=0.001,

               optimizer=None,

               tensorboard=False,

               tensorboard_log_frequency=100,

               log_frequency=100,

               **kwargs):

    """Create a new KerasModel.

      ignored.

    tensorboard: bool

      whether to log progress to TensorBoard during training

    tensorboard_log_frequency: int

      the frequency at which to log data to TensorBoard, measured in batches

    log_frequency: int

      The frequency at which to log data. Data is logged using `logging` by

      default. If `tensorboard` is set, data is also logged to TensorBoard.

    """

    super(KerasModel, self).__init__(

        model_instance=model, model_dir=model_dir, **kwargs)

    else:

      self.optimizer = optimizer

    self.tensorboard = tensorboard

    self.tensorboard_log_frequency = tensorboard_log_frequency

    self.log_frequency = log_frequency

    if self.tensorboard:

      self._summary_writer = tf.summary.create_file_writer(self.model_dir)

    if output_types is None:

      # Report progress and write checkpoints.

      averaged_batches += 1

      should_log = (current_step % self.tensorboard_log_frequency == 0)

      should_log = (current_step % self.log_frequency == 0)

      if should_log:

        avg_loss = float(avg_loss) / averaged_batches

        logger.info(

        keras_model,

        dc.models.losses.CategoricalCrossEntropy(),

        tensorboard=True,

        tensorboard_log_frequency=1)

        log_frequency=1)

    model.fit(dataset, nb_epoch=10)

    files_in_dir = os.listdir(model.model_dir)

    event_file = list(filter(lambda x: x.startswith("events"), files_in_dir))