tensorflow/models · error · ValueError

Not enought quantized model weights.

Error message

Not enought quantized model weights.

What it means

Error "Not enought quantized model weights." thrown in tensorflow/models.

Source

Thrown at official/projects/qat/vision/quantization/helper.py:92

  raise ValueError('Variable name {} is not supported.'.format(simple_name))


def copy_original_weights(original_model: tf_keras.Model,
                          quantized_model: tf_keras.Model):
  """Helper function that copy the original model weights to quantized model."""
  original_weight_value = original_model.get_weights()
  weight_values = quantized_model.get_weights()

  original_idx = 0
  for idx, weight in enumerate(quantized_model.weights):
    if not is_quantization_weight_name(weight.name):
      if original_idx >= len(original_weight_value):
        raise ValueError('Not enought original model weights.')
      weight_values[idx] = original_weight_value[original_idx]
      original_idx = original_idx + 1

  if original_idx < len(original_weight_value):
    raise ValueError('Not enought quantized model weights.')

  quantized_model.set_weights(weight_values)


class LayerQuantizerHelper(object):
  """Helper class that handles quantizers."""

  def __init__(self, *args, **kwargs):
    self._quantizers = {}
    self._quantizer_vars = {}
    super().__init__(*args, **kwargs)

  def _all_value_quantizer(self):
    return tfmot.quantization.keras.quantizers.AllValuesQuantizer(
        num_bits=8, per_axis=False, symmetric=False, narrow_range=False)

  def _moving_average_quantizer(self):
    return tfmot.quantization.keras.quantizers.MovingAverageQuantizer(

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/qat/vision/quantization/helper.py:92 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/317049e16895841b. Report an issue: GitHub.