tensorflow/models · error · ValueError

Unknown input file type {!r}

Error message

Unknown input file type {!r}

What it means

Error "Unknown input file type {!r}" thrown in tensorflow/models.

Source

Thrown at official/vision/tasks/video_classification.py:111

      ckpt = tf.train.Checkpoint(model=model)
      status = ckpt.read(ckpt_dir_or_file)
      status.expect_partial().assert_existing_objects_matched()
    elif self.task_config.init_checkpoint_modules == 'backbone':
      ckpt = tf.train.Checkpoint(backbone=model.backbone)
      status = ckpt.read(ckpt_dir_or_file)
      status.expect_partial().assert_existing_objects_matched()
    else:
      raise ValueError(
          "Only 'all' or 'backbone' can be used to initialize the model.")

    logging.info('Finished loading pretrained checkpoint from %s',
                 ckpt_dir_or_file)

  def _get_dataset_fn(self, params):
    if params.file_type == 'tfrecord':
      return tf.data.TFRecordDataset
    else:
      raise ValueError('Unknown input file type {!r}'.format(params.file_type))

  def _get_decoder_fn(self, params):
    if params.tfds_name:
      decoder = video_input.VideoTfdsDecoder(
          image_key=params.image_field_key, label_key=params.label_field_key)
    else:
      decoder = video_input.Decoder(
          image_key=params.image_field_key, label_key=params.label_field_key)
    if self.task_config.train_data.output_audio:
      assert self.task_config.train_data.audio_feature, 'audio feature is empty'
      decoder.add_feature(self.task_config.train_data.audio_feature,
                          tf.io.VarLenFeature(dtype=tf.float32))
    return decoder.decode

  def build_inputs(self,
                   params: exp_cfg.DataConfig,
                   input_context: Optional[tf.distribute.InputContext] = None):
    """Builds classification input."""

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Use a supported input file type such as 'tfrecord' or 'video' for the video classification input.
2. Check the input file type extension/config for typos.

When it happens

Trigger: Thrown at official/vision/tasks/video_classification.py:111 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tensorflow/models@e006f5f0d5 (2026-08-24). Data as JSON: /api/errors/7415d6895fc5b95e. Report an issue: GitHub.