tensorflow/models · error · ValueError

build_loss_fn() must be called after build_model().

Error message

build_loss_fn() must be called after build_model().

What it means

Error "build_loss_fn() must be called after build_model()." thrown in tensorflow/models.

Source

Thrown at official/legacy/detection/modeling/olnmask_model.py:293

    mask_roi_features = spatial_transform_ops.multilevel_crop_and_resize(
        fpn_features, rpn_rois, output_size=14)

    mask_outputs = self._mrcnn_head_fn(mask_roi_features, classes, is_training)

    if is_training:
      model_outputs.update({
          'mask_outputs':
              tf.nest.map_structure(lambda x: tf.cast(x, tf.float32),
                                    mask_outputs),
      })
    else:
      model_outputs.update({'detection_masks': tf.nn.sigmoid(mask_outputs)})

    return model_outputs

  def build_loss_fn(self):
    if self._keras_model is None:
      raise ValueError('build_loss_fn() must be called after build_model().')

    filter_fn = self.make_filter_trainable_variables_fn()
    trainable_variables = filter_fn(self._keras_model.trainable_variables)

    def _total_loss_fn(labels, outputs):
      if self._include_rpn_class:
        rpn_score_loss = self._rpn_score_loss_fn(outputs['rpn_score_outputs'],
                                                 labels['rpn_score_targets'])
      else:
        rpn_score_loss = 0.0
      if self._include_centerness:
        rpn_center_loss = self._rpn_center_loss_fn(
            outputs['rpn_center_outputs'], labels['rpn_center_targets'])
        rpn_box_loss = self._rpn_iou_loss_fn(
            outputs['rpn_box_outputs'], labels['rpn_box_targets'],
            labels['rpn_center_targets'])
      else:
        rpn_center_loss = 0.0

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/legacy/detection/modeling/olnmask_model.py:293 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/069debb842394c91. Report an issue: GitHub.