tensorflow_model_optimization/python/core/quantization/keras/default_8bit/default_8bit_quantize_registry.py [262:287]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  def get_quantize_config(self, layer):
    """Returns the quantization config for the given layer.

    Args:
      layer: input layer to return quantize config for.

    Returns:
      Returns the QuantizeConfig for the given layer.
    """
    if not self.supports(layer):
      raise ValueError(
          '`get_quantize_config()` called on an unsupported layer {}. Check '
          'if layer is supported by calling `supports()`. Alternatively, you '
          'can use `QuantizeConfig` to specify a behavior for your layer.'
          .format(layer.__class__))

    if self._is_supported_layer(layer.__class__):
      return self._get_quantize_config(layer.__class__)

    if self._is_rnn_layer(layer):
      weight_attrs = []
      activation_attrs = []
      for rnn_cell in self._get_rnn_cells(layer):
        quantize_info = self._get_quantize_info(rnn_cell.__class__)
        weight_attrs.append(quantize_info.weight_attrs)
        activation_attrs.append(quantize_info.activation_attrs)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow_model_optimization/python/core/quantization/keras/experimental/default_n_bit/default_n_bit_quantize_registry.py [292:317]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  def get_quantize_config(self, layer):
    """Returns the quantization config for the given layer.

    Args:
      layer: input layer to return quantize config for.

    Returns:
      Returns the QuantizeConfig for the given layer.
    """
    if not self.supports(layer):
      raise ValueError(
          '`get_quantize_config()` called on an unsupported layer {}. Check '
          'if layer is supported by calling `supports()`. Alternatively, you '
          'can use `QuantizeConfig` to specify a behavior for your layer.'
          .format(layer.__class__))

    if self._is_supported_layer(layer.__class__):
      return self._get_quantize_config(layer.__class__)

    if self._is_rnn_layer(layer):
      weight_attrs = []
      activation_attrs = []
      for rnn_cell in self._get_rnn_cells(layer):
        quantize_info = self._get_quantize_info(rnn_cell.__class__)
        weight_attrs.append(quantize_info.weight_attrs)
        activation_attrs.append(quantize_info.activation_attrs)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -