本文整理匯總了Python中object_detection.utils.np_box_ops.intersection方法的典型用法代碼示例。如果您正苦於以下問題：Python np_box_ops.intersection方法的具體用法？Python np_box_ops.intersection怎麽用？Python np_box_ops.intersection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_box_ops的用法示例。
在下文中一共展示了np_box_ops.intersection方法的4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: testIntersection
# 需要導入模塊: from object_detection.utils import np_box_ops [as 別名]
# 或者: from object_detection.utils.np_box_ops import intersection [as 別名]
def testIntersection(self):
intersection = np_box_ops.intersection(self.boxes1, self.boxes2)
expected_intersection = np.array([[2.0, 0.0, 6.0], [1.0, 0.0, 5.0]],
dtype=float)
self.assertAllClose(intersection, expected_intersection) 示例2: intersection
# 需要導入模塊: from object_detection.utils import np_box_ops [as 別名]
# 或者: from object_detection.utils.np_box_ops import intersection [as 別名]
def intersection(boxlist1, boxlist2):
"""Compute pairwise intersection areas between boxes.
Args:
boxlist1: BoxList holding N boxes
boxlist2: BoxList holding M boxes
Returns:
a numpy array with shape [N*M] representing pairwise intersection area
"""
return np_box_ops.intersection(boxlist1.get(), boxlist2.get()) 示例3: iou
# 需要導入模塊: from object_detection.utils import np_box_ops [as 別名]
# 或者: from object_detection.utils.np_box_ops import intersection [as 別名]
def iou(boxlist1, boxlist2):
"""Computes pairwise intersection-over-union between box collections.
Args:
boxlist1: BoxList holding N boxes
boxlist2: BoxList holding M boxes
Returns:
a numpy array with shape [N, M] representing pairwise iou scores.
"""
return np_box_ops.iou(boxlist1.get(), boxlist2.get()) 示例4: ioa
# 需要導入模塊: from object_detection.utils import np_box_ops [as 別名]
# 或者: from object_detection.utils.np_box_ops import intersection [as 別名]
def ioa(boxlist1, boxlist2):
"""Computes pairwise intersection-over-area between box collections.
Intersection-over-area (ioa) between two boxes box1 and box2 is defined as
their intersection area over box2's area. Note that ioa is not symmetric,
that is, IOA(box1, box2) != IOA(box2, box1).
Args:
boxlist1: BoxList holding N boxes
boxlist2: BoxList holding M boxes
Returns:
a numpy array with shape [N, M] representing pairwise ioa scores.
"""
return np_box_ops.ioa(boxlist1.get(), boxlist2.get())