本文整理汇总了Python中object_detection.utils.np_mask_ops.ioa方法的典型用法代码示例。如果您正苦于以下问题：Python np_mask_ops.ioa方法的具体用法？Python np_mask_ops.ioa怎么用？Python np_mask_ops.ioa使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类object_detection.utils.np_mask_ops的用法示例。
在下文中一共展示了np_mask_ops.ioa方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: prune_non_overlapping_masks
# 需要导入模块: from object_detection.utils import np_mask_ops [as 别名]
# 或者: from object_detection.utils.np_mask_ops import ioa [as 别名]
def prune_non_overlapping_masks(box_mask_list1, box_mask_list2, minoverlap=0.0):
"""Prunes the boxes in list1 that overlap less than thresh with list2.
For each mask in box_mask_list1, we want its IOA to be more than minoverlap
with at least one of the masks in box_mask_list2. If it does not, we remove
it. If the masks are not full size image, we do the pruning based on boxes.
Args:
box_mask_list1: np_box_mask_list.BoxMaskList holding N boxes and masks.
box_mask_list2: np_box_mask_list.BoxMaskList holding M boxes and masks.
minoverlap: Minimum required overlap between boxes, to count them as
overlapping.
Returns:
A pruned box_mask_list with size [N', 4].
"""
intersection_over_area = ioa(box_mask_list2, box_mask_list1) # [M, N] tensor
intersection_over_area = np.amax(intersection_over_area, axis=0) # [N] tensor
keep_bool = np.greater_equal(intersection_over_area, np.array(minoverlap))
keep_inds = np.nonzero(keep_bool)[0]
new_box_mask_list1 = gather(box_mask_list1, keep_inds)
return new_box_mask_list1 示例2: testIOA
# 需要导入模块: from object_detection.utils import np_mask_ops [as 别名]
# 或者: from object_detection.utils.np_mask_ops import ioa [as 别名]
def testIOA(self):
ioa21 = np_mask_ops.ioa(self.masks1, self.masks2)
expected_ioa21 = np.array([[1.0, 0.0, 8.0/25.0],
[0.0, 9.0/15.0, 7.0/25.0]],
dtype=np.float32)
self.assertAllClose(ioa21, expected_ioa21) 示例3: ioa
# 需要导入模块: from object_detection.utils import np_mask_ops [as 别名]
# 或者: from object_detection.utils.np_mask_ops import ioa [as 别名]
def ioa(box_mask_list1, box_mask_list2):
"""Computes pairwise intersection-over-area between box and mask collections.
Intersection-over-area (ioa) between two masks mask1 and mask2 is defined as
their intersection area over mask2's area. Note that ioa is not symmetric,
that is, IOA(mask1, mask2) != IOA(mask2, mask1).
Args:
box_mask_list1: np_box_mask_list.BoxMaskList holding N boxes and masks
box_mask_list2: np_box_mask_list.BoxMaskList holding M boxes and masks
Returns:
a numpy array with shape [N, M] representing pairwise ioa scores.
"""
return np_mask_ops.ioa(box_mask_list1.get_masks(), box_mask_list2.get_masks())