本文整理匯總了Python中object_detection.utils.np_mask_ops.iou方法的典型用法代碼示例。如果您正苦於以下問題：Python np_mask_ops.iou方法的具體用法？Python np_mask_ops.iou怎麽用？Python np_mask_ops.iou使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類object_detection.utils.np_mask_ops的用法示例。
在下文中一共展示了np_mask_ops.iou方法的3個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: testIOU
# 需要導入模塊: from object_detection.utils import np_mask_ops [as 別名]
# 或者: from object_detection.utils.np_mask_ops import iou [as 別名]
def testIOU(self):
iou = np_mask_ops.iou(self.masks1, self.masks2)
expected_iou = np.array(
[[1.0, 0.0, 8.0/25.0], [0.0, 9.0 / 16.0, 7.0 / 28.0]], dtype=np.float32)
self.assertAllClose(iou, expected_iou) 示例2: iou
# 需要導入模塊: from object_detection.utils import np_mask_ops [as 別名]
# 或者: from object_detection.utils.np_mask_ops import iou [as 別名]
def iou(box_mask_list1, box_mask_list2):
"""Computes pairwise intersection-over-union between box and mask collections.
Args:
box_mask_list1: BoxMaskList holding N boxes and masks
box_mask_list2: BoxMaskList holding M boxes and masks
Returns:
a numpy array with shape [N, M] representing pairwise iou scores.
"""
return np_mask_ops.iou(box_mask_list1.get_masks(),
box_mask_list2.get_masks()) 示例3: evaluate
# 需要導入模塊: from object_detection.utils import np_mask_ops [as 別名]
# 或者: from object_detection.utils.np_mask_ops import iou [as 別名]
def evaluate(self):
"""Evaluates the detection masks and returns a dictionary of coco metrics.
Returns:
A dictionary holding -
1. summary_metric:
'PanopticQuality@%.2fIOU': mean panoptic quality averaged over classes at
the required IOU.
'SegmentationQuality@%.2fIOU': mean segmentation quality averaged over
classes at the required IOU.
'RecognitionQuality@%.2fIOU': mean recognition quality averaged over
classes at the required IOU.
'NumValidClasses': number of valid classes. A valid class should have at
least one normal (is_crowd=0) groundtruth mask or one predicted mask.
'NumTotalClasses': number of total classes.
2. per_category_pq: if include_metrics_per_category is True, category
specific results with keys of the form:
'PanopticQuality@%.2fIOU_ByCategory/category'.
"""
# Evaluate and accumulate the iou/tp/fp/fn.
sum_tp_iou, sum_num_tp, sum_num_fp, sum_num_fn = self._evaluate_all_masks()
# Compute PQ metric for each category and average over all classes.
mask_metrics = self._compute_panoptic_metrics(sum_tp_iou, sum_num_tp,
sum_num_fp, sum_num_fn)
return mask_metrics