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/shapemask_model.py:156

        'coarse_mask_logits': coarse_mask_logits,
        'prior_masks': prior_masks,
    }

    if not is_training:
      model_outputs.update({
          'num_detections': valid_detections,
          'detection_boxes': valid_boxes,
          'detection_outer_boxes': valid_outer_boxes,
          'detection_masks': fine_mask_logits,
          'detection_classes': valid_classes,
          'detection_scores': valid_scores,
      })

    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):
      cls_loss = self._cls_loss_fn(outputs['cls_outputs'],
                                   labels['cls_targets'],
                                   labels['num_positives'])
      box_loss = self._box_loss_fn(outputs['box_outputs'],
                                   labels['box_targets'],
                                   labels['num_positives'])

      # Adds Shapemask model losses.
      shape_prior_loss = self._shapemask_prior_loss_fn(outputs['prior_masks'],
                                                       labels['mask_targets'],
                                                       labels['mask_is_valid'])
      coarse_mask_loss = self._shapemask_loss_fn(outputs['coarse_mask_logits'],
                                                 labels['mask_targets'],

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/legacy/detection/modeling/shapemask_model.py:156 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/eb315ef35ca29bde. Report an issue: GitHub.