当前位置: 首页>>代码示例>>Python>>正文


Python keypoint_ops.to_normalized_coordinates方法代码示例

本文整理汇总了Python中object_detection.core.keypoint_ops.to_normalized_coordinates方法的典型用法代码示例。如果您正苦于以下问题:Python keypoint_ops.to_normalized_coordinates方法的具体用法?Python keypoint_ops.to_normalized_coordinates怎么用?Python keypoint_ops.to_normalized_coordinates使用的例子?那么, 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object_detection.core.keypoint_ops的用法示例。


在下文中一共展示了keypoint_ops.to_normalized_coordinates方法的2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_to_normalized_coordinates

# 需要导入模块: from object_detection.core import keypoint_ops [as 别名]
# 或者: from object_detection.core.keypoint_ops import to_normalized_coordinates [as 别名]
def test_to_normalized_coordinates(self):
    keypoints = tf.constant([
        [[10., 30.], [30., 45.]],
        [[20., 0.], [40., 60.]]
    ])
    output = keypoint_ops.to_normalized_coordinates(
        keypoints, 40, 60)
    expected_keypoints = tf.constant([
        [[0.25, 0.5], [0.75, 0.75]],
        [[0.5, 0.0], [1.0, 1.0]]
    ])

    with self.test_session() as sess:
      output_, expected_keypoints_ = sess.run([output, expected_keypoints])
      self.assertAllClose(output_, expected_keypoints_) 
开发者ID:ringringyi,项目名称:DOTA_models,代码行数:17,代码来源:keypoint_ops_test.py

示例2: test_to_normalized_coordinates_already_normalized

# 需要导入模块: from object_detection.core import keypoint_ops [as 别名]
# 或者: from object_detection.core.keypoint_ops import to_normalized_coordinates [as 别名]
def test_to_normalized_coordinates_already_normalized(self):
    keypoints = tf.constant([
        [[0.25, 0.5], [0.75, 0.75]],
        [[0.5, 0.0], [1.0, 1.0]]
    ])
    output = keypoint_ops.to_normalized_coordinates(
        keypoints, 40, 60)

    with self.test_session() as sess:
      with self.assertRaisesOpError('assertion failed'):
        sess.run(output) 
开发者ID:ringringyi,项目名称:DOTA_models,代码行数:13,代码来源:keypoint_ops_test.py


注:本文中的object_detection.core.keypoint_ops.to_normalized_coordinates方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。