当前位置: 首页>>代码示例>>Python>>正文


Python keypoint_ops.clip_to_window方法代码示例

本文整理汇总了Python中object_detection.core.keypoint_ops.clip_to_window方法的典型用法代码示例。如果您正苦于以下问题:Python keypoint_ops.clip_to_window方法的具体用法?Python keypoint_ops.clip_to_window怎么用?Python keypoint_ops.clip_to_window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.clip_to_window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_clip_to_window

# 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 clip_to_window [as 别名]
def test_clip_to_window(self):
    keypoints = tf.constant([
        [[0.25, 0.5], [0.75, 0.75]],
        [[0.5, 0.0], [1.0, 1.0]]
    ])
    window = tf.constant([0.25, 0.25, 0.75, 0.75])

    expected_keypoints = tf.constant([
        [[0.25, 0.5], [0.75, 0.75]],
        [[0.5, 0.25], [0.75, 0.75]]
    ])
    output = keypoint_ops.clip_to_window(keypoints, window)

    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:18,代码来源:keypoint_ops_test.py

示例2: test_clip_to_window

# 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 clip_to_window [as 别名]
def test_clip_to_window(self):
    def graph_fn():
      keypoints = tf.constant([
          [[0.25, 0.5], [0.75, 0.75]],
          [[0.5, 0.0], [1.0, 1.0]]
      ])
      window = tf.constant([0.25, 0.25, 0.75, 0.75])

      expected_keypoints = tf.constant([
          [[0.25, 0.5], [0.75, 0.75]],
          [[0.5, 0.25], [0.75, 0.75]]
      ])
      output = keypoint_ops.clip_to_window(keypoints, window)
      return output, expected_keypoints
    output, expected_keypoints = self.execute(graph_fn, [])
    self.assertAllClose(output, expected_keypoints) 
开发者ID:tensorflow,项目名称:models,代码行数:18,代码来源:keypoint_ops_test.py

示例3: convert_strided_predictions_to_normalized_boxes

# 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 clip_to_window [as 别名]
def convert_strided_predictions_to_normalized_boxes(boxes, stride,
                                                    true_image_shapes):
  """Converts predictions in the output space to normalized boxes.

  Boxes falling outside the valid image boundary are clipped to be on the
  boundary.

  Args:
    boxes: A tensor of shape [batch_size, num_boxes, 4] holding the raw
     coordinates of boxes in the model's output space.
    stride: The stride in the output space.
    true_image_shapes: A tensor of shape [batch_size, 3] representing the true
      shape of the input not considering padding.

  Returns:
    boxes: A tensor of shape [batch_size, num_boxes, 4] representing the
      coordinates of the normalized boxes.
  """

  def _normalize_boxlist(args):

    boxes, height, width = args
    boxes = box_list_ops.scale(boxes, stride, stride)
    boxes = box_list_ops.to_normalized_coordinates(boxes, height, width)
    boxes = box_list_ops.clip_to_window(boxes, [0., 0., 1., 1.],
                                        filter_nonoverlapping=False)
    return boxes

  box_lists = [box_list.BoxList(boxes) for boxes in tf.unstack(boxes, axis=0)]
  true_heights, true_widths, _ = tf.unstack(true_image_shapes, axis=1)

  true_heights_list = tf.unstack(true_heights, axis=0)
  true_widths_list = tf.unstack(true_widths, axis=0)

  box_lists = list(map(_normalize_boxlist,
                       zip(box_lists, true_heights_list, true_widths_list)))
  boxes = tf.stack([box_list_instance.get() for
                    box_list_instance in box_lists], axis=0)

  return boxes 
开发者ID:tensorflow,项目名称:models,代码行数:42,代码来源:center_net_meta_arch.py


注:本文中的object_detection.core.keypoint_ops.clip_to_window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。