本文整理汇总了Python中object_detection.core.box_list_ops.prune_non_overlapping_boxes方法的典型用法代码示例。如果您正苦于以下问题：Python box_list_ops.prune_non_overlapping_boxes方法的具体用法？Python box_list_ops.prune_non_overlapping_boxes怎么用？Python box_list_ops.prune_non_overlapping_boxes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.core.box_list_ops的用法示例。
在下文中一共展示了box_list_ops.prune_non_overlapping_boxes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: test_prune_non_overlapping_boxes
# 需要导入模块: from object_detection.core import box_list_ops [as 别名]
# 或者: from object_detection.core.box_list_ops import prune_non_overlapping_boxes [as 别名]
def test_prune_non_overlapping_boxes(self):
corners1 = tf.constant([[4.0, 3.0, 7.0, 5.0], [5.0, 6.0, 10.0, 7.0]])
corners2 = tf.constant([[3.0, 4.0, 6.0, 8.0], [14.0, 14.0, 15.0, 15.0],
[0.0, 0.0, 20.0, 20.0]])
boxes1 = box_list.BoxList(corners1)
boxes2 = box_list.BoxList(corners2)
minoverlap = 0.5
exp_output_1 = boxes1
exp_output_2 = box_list.BoxList(tf.constant(0.0, shape=[0, 4]))
output_1, keep_indices_1 = box_list_ops.prune_non_overlapping_boxes(
boxes1, boxes2, min_overlap=minoverlap)
output_2, keep_indices_2 = box_list_ops.prune_non_overlapping_boxes(
boxes2, boxes1, min_overlap=minoverlap)
with self.test_session() as sess:
(output_1_, keep_indices_1_, output_2_, keep_indices_2_, exp_output_1_,
exp_output_2_) = sess.run(
[output_1.get(), keep_indices_1,
output_2.get(), keep_indices_2,
exp_output_1.get(), exp_output_2.get()])
self.assertAllClose(output_1_, exp_output_1_)
self.assertAllClose(output_2_, exp_output_2_)
self.assertAllEqual(keep_indices_1_, [0, 1])
self.assertAllEqual(keep_indices_2_, []) 示例2: test_prune_non_overlapping_boxes
# 需要导入模块: from object_detection.core import box_list_ops [as 别名]
# 或者: from object_detection.core.box_list_ops import prune_non_overlapping_boxes [as 别名]
def test_prune_non_overlapping_boxes(self):
def graph_fn():
corners1 = tf.constant([[4.0, 3.0, 7.0, 5.0], [5.0, 6.0, 10.0, 7.0]])
corners2 = tf.constant([[3.0, 4.0, 6.0, 8.0], [14.0, 14.0, 15.0, 15.0],
[0.0, 0.0, 20.0, 20.0]])
boxes1 = box_list.BoxList(corners1)
boxes2 = box_list.BoxList(corners2)
minoverlap = 0.5
exp_output_1 = boxes1
exp_output_2 = box_list.BoxList(tf.constant(0.0, shape=[0, 4]))
output_1, keep_indices_1 = box_list_ops.prune_non_overlapping_boxes(
boxes1, boxes2, min_overlap=minoverlap)
output_2, keep_indices_2 = box_list_ops.prune_non_overlapping_boxes(
boxes2, boxes1, min_overlap=minoverlap)
return (output_1.get(), keep_indices_1, output_2.get(), keep_indices_2,
exp_output_1.get(), exp_output_2.get())
(output_1_, keep_indices_1_, output_2_, keep_indices_2_, exp_output_1_,
exp_output_2_) = self.execute_cpu(graph_fn, [])
self.assertAllClose(output_1_, exp_output_1_)
self.assertAllClose(output_2_, exp_output_2_)
self.assertAllEqual(keep_indices_1_, [0, 1])
self.assertAllEqual(keep_indices_2_, []) 示例3: test_prune_non_overlapping_boxes
# 需要导入模块: from object_detection.core import box_list_ops [as 别名]
# 或者: from object_detection.core.box_list_ops import prune_non_overlapping_boxes [as 别名]
def test_prune_non_overlapping_boxes(self):
corners1 = tf.constant([[4.0, 3.0, 7.0, 5.0], [5.0, 6.0, 10.0, 7.0]])
corners2 = tf.constant([[3.0, 4.0, 6.0, 8.0], [14.0, 14.0, 15.0, 15.0],
[0.0, 0.0, 20.0, 20.0]])
boxes1 = box_list.BoxList(corners1)
boxes2 = box_list.BoxList(corners2)
minoverlap = 0.5
exp_output_1 = boxes1
exp_output_2 = box_list.BoxList(tf.constant(0.0, shape=[0, 4]))
output_1, keep_indices_1 = box_list_ops.prune_non_overlapping_boxes(
boxes1, boxes2, min_overlap=minoverlap)
output_2, keep_indices_2 = box_list_ops.prune_non_overlapping_boxes(
boxes2, boxes1, min_overlap=minoverlap)
with self.test_session() as sess:
(output_1_,
keep_indices_1_,
output_2_,
keep_indices_2_,
exp_output_1_,
exp_output_2_) = sess.run([output_1.get(),
keep_indices_1,
output_2.get(),
keep_indices_2,
exp_output_1.get(),
exp_output_2.get()])
self.assertAllClose(output_1_, exp_output_1_)
self.assertAllClose(output_2_, exp_output_2_)
self.assertAllEqual(keep_indices_1_, [0, 1])
self.assertAllEqual(keep_indices_2_, [])