Python coco_tools.ExportSingleImageDetectionMasksToCoco方法代码示例

# 需要导入模块: from object_detection.metrics import coco_tools [as 别名]
# 或者: from object_detection.metrics.coco_tools import ExportSingleImageDetectionMasksToCoco [as 别名]
def testSingleImageDetectionMaskExport(self):
    masks = np.array(
        [[[1, 1,], [1, 1]],
         [[0, 0], [0, 1]],
         [[0, 0], [0, 0]]], dtype=np.uint8)
    classes = np.array([1, 2, 3], dtype=np.int32)
    scores = np.array([0.8, 0.2, 0.7], dtype=np.float32)
    coco_annotations = coco_tools.ExportSingleImageDetectionMasksToCoco(
        image_id='first_image',
        category_id_set=set([1, 2, 3]),
        detection_classes=classes,
        detection_scores=scores,
        detection_masks=masks)
    expected_counts = ['04', '31', '4']
    for i, mask_annotation in enumerate(coco_annotations):
      self.assertEqual(mask_annotation['segmentation']['counts'],
                       expected_counts[i])
      self.assertTrue(np.all(np.equal(mask.decode(
          mask_annotation['segmentation']), masks[i])))
      self.assertEqual(mask_annotation['image_id'], 'first_image')
      self.assertEqual(mask_annotation['category_id'], classes[i])
      self.assertAlmostEqual(mask_annotation['score'], scores[i]) 

# 需要导入模块: from object_detection.metrics import coco_tools [as 别名]
# 或者: from object_detection.metrics.coco_tools import ExportSingleImageDetectionMasksToCoco [as 别名]
def add_single_detected_image_info(self,
                                     image_id,
                                     detections_dict):
    """Adds detections for a single image to be used for evaluation.

    If a detection has already been added for this image id, a warning is
    logged, and the detection is skipped.

    Args:
      image_id: A unique string/integer identifier for the image.
      detections_dict: A dictionary containing -
        DetectionResultFields.detection_scores: float32 numpy array of shape
          [num_boxes] containing detection scores for the boxes.
        DetectionResultFields.detection_classes: integer numpy array of shape
          [num_boxes] containing 1-indexed detection classes for the boxes.
        DetectionResultFields.detection_masks: optional uint8 numpy array of
          shape [num_boxes, image_height, image_width] containing instance
          masks corresponding to the boxes. The elements of the array must be
          in {0, 1}.

    Raises:
      ValueError: If groundtruth for the image_id is not available or if
        spatial shapes of groundtruth_instance_masks and detection_masks are
        incompatible.
    """
    if image_id not in self._image_id_to_mask_shape_map:
      raise ValueError('Missing groundtruth for image id: {}'.format(image_id))

    if image_id in self._image_ids_with_detections:
      tf.logging.warning('Ignoring detection with image id %s since it was '
                         'previously added', image_id)
      return

    groundtruth_masks_shape = self._image_id_to_mask_shape_map[image_id]
    detection_masks = detections_dict[standard_fields.DetectionResultFields.
                                      detection_masks]
    if groundtruth_masks_shape[1:] != detection_masks.shape[1:]:
      raise ValueError('Spatial shape of groundtruth masks and detection masks '
                       'are incompatible: {} vs {}'.format(
                           groundtruth_masks_shape,
                           detection_masks.shape))
    _check_mask_type_and_value(standard_fields.DetectionResultFields.
                               detection_masks,
                               detection_masks)
    self._detection_masks_list.extend(
        coco_tools.ExportSingleImageDetectionMasksToCoco(
            image_id=image_id,
            category_id_set=self._category_id_set,
            detection_masks=detection_masks,
            detection_scores=detections_dict[standard_fields.
                                             DetectionResultFields.
                                             detection_scores],
            detection_classes=detections_dict[standard_fields.
                                              DetectionResultFields.
                                              detection_classes]))
    self._image_ids_with_detections.update([image_id]) 

# 需要导入模块: from object_detection.metrics import coco_tools [as 别名]
# 或者: from object_detection.metrics.coco_tools import ExportSingleImageDetectionMasksToCoco [as 别名]
def add_single_detected_image_info(self,
                                     image_id,
                                     detections_dict):
    """Adds detections for a single image to be used for evaluation.

    Args:
      image_id: A unique string/integer identifier for the image.
      detections_dict: A dictionary containing -
        DetectionResultFields.detection_scores: float32 numpy array of shape
          [num_boxes] containing detection scores for the boxes.
        DetectionResultFields.detection_classes: integer numpy array of shape
          [num_boxes] containing 1-indexed detection classes for the boxes.
        DetectionResultFields.detection_masks: optional uint8 numpy array of
          shape [num_boxes, image_height, image_width] containing instance
          masks corresponding to the boxes. The elements of the array must be
          in {0, 1}.

    Raises:
      ValueError: If groundtruth for the image_id is not available or if
        spatial shapes of groundtruth_instance_masks and detection_masks are
        incompatible.
    """
    if image_id not in self._image_id_to_mask_shape_map:
      raise ValueError('Missing groundtruth for image id: {}'.format(image_id))

    if image_id in self._image_ids_with_detections:
      tf.logging.warning('Ignoring detection with image id %s since it was '
                         'previously added', image_id)
      return

    groundtruth_masks_shape = self._image_id_to_mask_shape_map[image_id]
    detection_masks = detections_dict[standard_fields.DetectionResultFields.
                                      detection_masks]
    if groundtruth_masks_shape[1:] != detection_masks.shape[1:]:
      raise ValueError('Spatial shape of groundtruth masks and detection masks '
                       'are incompatible: {} vs {}'.format(
                           groundtruth_masks_shape,
                           detection_masks.shape))
    _check_mask_type_and_value(standard_fields.DetectionResultFields.
                               detection_masks,
                               detection_masks)
    self._detection_masks_list.extend(
        coco_tools.ExportSingleImageDetectionMasksToCoco(
            image_id=image_id,
            category_id_set=self._category_id_set,
            detection_masks=detection_masks,
            detection_scores=detections_dict[standard_fields.
                                             DetectionResultFields.
                                             detection_scores],
            detection_classes=detections_dict[standard_fields.
                                              DetectionResultFields.
                                              detection_classes]))
    self._image_ids_with_detections.update([image_id])