tensorflow/models · error · ValueError

Unused logit_activation option inherited from vision Segment

Error message

Unused logit_activation option inherited from vision SegmentationHead modeling config.

What it means

Error "Unused logit_activation option inherited from vision SegmentationHead modeling config." thrown in tensorflow/models.

Source

Thrown at official/projects/qat/vision/modeling/layers/nn_layers.py:316

        'low_level': low_level,
        'low_level_num_filters': low_level_num_filters,
        'num_decoder_filters': num_decoder_filters,
        'activation': activation,
        'use_sync_bn': use_sync_bn,
        'norm_momentum': norm_momentum,
        'norm_epsilon': norm_epsilon,
        'kernel_regularizer': kernel_regularizer,
        'bias_regularizer': bias_regularizer,
    }
    if tf_keras.backend.image_data_format() == 'channels_last':
      self._bn_axis = -1
    else:
      self._bn_axis = 1
    self._activation_layer = tfmot.quantization.keras.QuantizeWrapperV2(
        tf_utils.get_activation(activation, use_keras_layer=True),
        configs.Default8BitActivationQuantizeConfig())
    if logit_activation:
      raise ValueError('Unused logit_activation option inherited from '
                       'vision SegmentationHead modeling config.')

  def build(self, input_shape: Sequence[tf.TensorShape]):
    """Creates the variables of the segmentation head."""
    # When input_shape is a list/tuple, the first corresponds to backbone
    # features used for resizing the decoder features (the second) if feature
    # fusion type is `deeplabv3plus`.
    backbone_shape = input_shape[0]
    use_depthwise_convolution = self._config_dict['use_depthwise_convolution']
    random_initializer = tf_keras.initializers.RandomNormal(stddev=0.01)
    conv_kwargs = {
        'kernel_size': 3 if not use_depthwise_convolution else 1,
        'padding': 'same',
        'use_bias': False,
        'kernel_initializer': random_initializer,
        'kernel_regularizer': self._config_dict['kernel_regularizer'],
    }

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/qat/vision/modeling/layers/nn_layers.py:316 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/eca61a10e870fa2f. Report an issue: GitHub.