tensorflow/models · error · ValueError

Additional classifier layer is needed if final decoder proje

Error message

Additional classifier layer is needed if final decoder projected filters does not match num_classes!

What it means

Error "Additional classifier layer is needed if final decoder projected filters does not match num_classes!" thrown in tensorflow/models.

Source

Thrown at official/projects/mosaic/qat/modeling/heads/mosaic_head.py:172

            use_sync_bn=use_sync_bn,
            batchnorm_momentum=batchnorm_momentum,
            batchnorm_epsilon=batchnorm_epsilon,
            activation=activation,
            kernel_initializer=kernel_initializer,
            kernel_regularizer=kernel_regularizer,
            interpolation=interpolation)
        self._merge_stages.append(sum_merge_stage)
      else:
        raise ValueError(
            'A stage merge style in MOSAIC Decoder can only be concat_merge '
            'or sum_merge.')

    # Concat merge or sum merge does not require an additional classifer layer
    # unless the final decoder projected filter does not match num_classes.
    final_decoder_projected_filter = decoder_projected_filters[-1]
    if (final_decoder_projected_filter != num_classes and
        not use_additional_classifier_layer):
      raise ValueError('Additional classifier layer is needed if final decoder '
                       'projected filters does not match num_classes!')
    self._use_additional_classifier_layer = use_additional_classifier_layer
    if use_additional_classifier_layer:
      # This additional classification layer uses different kernel
      # initializers and bias compared to earlier blocks.
      self._pixelwise_classifier = helper.Conv2DQuantized(
          name='pixelwise_classifier',
          filters=num_classes,
          kernel_size=classifier_kernel_size,
          padding='same',
          bias_initializer=tf.zeros_initializer(),
          kernel_initializer=tf_keras.initializers.RandomNormal(stddev=0.01),
          kernel_regularizer=kernel_regularizer,
          bias_regularizer=bias_regularizer,
          activation=helper.NoOpActivation(),
          use_bias=True)

      self._activation_fn = tfmot.quantization.keras.QuantizeWrapperV2(

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/mosaic/qat/modeling/heads/mosaic_head.py:172 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/ec82b0708b56e906. Report an issue: GitHub.