tensorflow/models · error · ValueError

An NMS algorithm is required for detection generator

Error message

An NMS algorithm is required for detection generator

What it means

Error "An NMS algorithm is required for detection generator" thrown in tensorflow/models.

Source

Thrown at official/projects/pointpillars/modeling/models.py:104

    if image_shape is None:
      raise ValueError('Image_shape should not be None for evaluation.')
    if anchor_boxes is None:
      # Generate anchors if needed.
      anchor_boxes = utils.generate_anchors(
          self._min_level,
          self._max_level,
          self._image_size,
          self._anchor_sizes,
      )
      for l in anchor_boxes:
        anchor_boxes[l] = tf.tile(
            tf.expand_dims(anchor_boxes[l], axis=0),
            [tf.shape(image_shape)[0], 1, 1, 1])

    # Generate detected boxes.
    if not self._detection_generator.get_config()['apply_nms']:
      raise ValueError('An NMS algorithm is required for detection generator')
    detections = self._detection_generator(raw_boxes, raw_scores,
                                           anchor_boxes, image_shape,
                                           raw_attributes)
    outputs.update({
        'boxes': detections['detection_boxes'],
        'scores': detections['detection_scores'],
        'classes': detections['detection_classes'],
        'num_detections': detections['num_detections'],
        'attributes': detections['detection_attributes'],
    })
    return outputs

  def call(self,  # pytype: disable=annotation-type-mismatch,signature-mismatch
           pillars: tf.Tensor,
           indices: tf.Tensor,
           image_shape: Optional[tf.Tensor] = None,
           anchor_boxes: Optional[Mapping[str, tf.Tensor]] = None,
           training: bool = None) -> Mapping[str, Any]:  # pyrefly: ignore[bad-function-definition]

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/pointpillars/modeling/models.py:104 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/e891d2c4db193549. Report an issue: GitHub.