Method convert

tensorflow/lite/python/lite.py:871–995

Converts a TensorFlow GraphDef based on instance variables. Returns: The converted data in serialized format. Either a TFLite Flatbuffer or a Graphviz graph depending on value in `output_format`. Raises: ValueError: Input shape is not specified. None value

(self)

    return object.__getattribute__(self, name)

  def convert(self):
    """Converts a TensorFlow GraphDef based on instance variables.

    Returns:
      The converted data in serialized format. Either a TFLite Flatbuffer or a
      Graphviz graph depending on value in `output_format`.

    Raises:
      ValueError:
        Input shape is not specified.
        None value for dimension in input_tensor.
    """
    # Checks dimensions in input tensor.
    if self._has_valid_tensors():
      for tensor in self._input_tensors:
        shape = tensor.shape
        if not shape:
          raise ValueError("Provide an input shape for input array "
                           "'{0}'.".format(_get_tensor_name(tensor)))
        # Note that shape_list might be empty for scalar shapes.
        shape_list = shape.as_list()
        if None in shape_list[1:]:
          raise ValueError(
              "None is only supported in the 1st dimension. Tensor '{0}' has "
              "invalid shape '{1}'.".format(
                  _get_tensor_name(tensor), shape_list))
        elif shape_list and shape_list[0] is None:
          self._set_batch_size(batch_size=1)

    # Get quantization stats. Ensures there is one stat per name if the stats
    # are specified.
    if self.quantized_input_stats:
      quantized_stats = []
      invalid_stats = []
      for name in self.get_input_arrays():
        if name in self.quantized_input_stats:
          quantized_stats.append(self.quantized_input_stats[name])
        else:
          invalid_stats.append(name)

      if invalid_stats:
        raise ValueError("Quantization input stats are not available for input "
                         "tensors '{0}'.".format(",".join(invalid_stats)))
    else:
      quantized_stats = None

    self._validate_quantization()
    self._validate_representative_dataset()

    toco_inference_input_type = self.inference_input_type
    inference_input_type = self.inference_input_type
    inference_output_type = self.inference_output_type
    post_training_optimize = self._is_post_training_optimize()
    if post_training_optimize:
      # Post training optimizations require that TOCO outputs a float model.
      if self.inference_type != constants.FLOAT:
        raise ValueError(
            "`optimizations` require that `inference_type` is set to float.")