tensorflow_model_optimization/python/core/quantization/keras/default_8bit/default_8bit_quantize_registry.py [430:451]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      for weight_attr in weight_attrs_cell:
        current_weight = getattr(rnn_cell, weight_attr)
        quantize_weight = quantize_weights[i]

        if current_weight.shape != quantize_weight.shape:
          raise ValueError('Existing layer weight shape {} is incompatible with'
                           'provided weight shape {}'.format(
                               current_weight.shape, quantize_weight.shape))

        setattr(rnn_cell, weight_attr, quantize_weight)
        i += 1

  def set_quantize_activations(self, layer, quantize_activations):
    flattened_activation_attrs = self._flatten(self.activation_attrs)
    if len(flattened_activation_attrs) != len(quantize_activations):
      raise ValueError(
          '`set_quantize_activations` called on layer {} with {} '
          'activation parameters, but layer expects {} values.'.format(
              layer.name, len(quantize_activations),
              len(flattened_activation_attrs)))

    i = 0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow_model_optimization/python/core/quantization/keras/experimental/default_n_bit/default_n_bit_quantize_registry.py [471:492]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      for weight_attr in weight_attrs_cell:
        current_weight = getattr(rnn_cell, weight_attr)
        quantize_weight = quantize_weights[i]

        if current_weight.shape != quantize_weight.shape:
          raise ValueError('Existing layer weight shape {} is incompatible with'
                           'provided weight shape {}'.format(
                               current_weight.shape, quantize_weight.shape))

        setattr(rnn_cell, weight_attr, quantize_weight)
        i += 1

  def set_quantize_activations(self, layer, quantize_activations):
    flattened_activation_attrs = self._flatten(self.activation_attrs)
    if len(flattened_activation_attrs) != len(quantize_activations):
      raise ValueError(
          '`set_quantize_activations` called on layer {} with {} '
          'activation parameters, but layer expects {} values.'.format(
              layer.name, len(quantize_activations),
              len(flattened_activation_attrs)))

    i = 0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -