當前位置: 首頁>>代碼示例>>Python>>正文


Python ops.reframe_box_masks_to_image_masks方法代碼示例

本文整理匯總了Python中object_detection.utils.ops.reframe_box_masks_to_image_masks方法的典型用法代碼示例。如果您正苦於以下問題:Python ops.reframe_box_masks_to_image_masks方法的具體用法?Python ops.reframe_box_masks_to_image_masks怎麽用?Python ops.reframe_box_masks_to_image_masks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object_detection.utils.ops的用法示例。


在下文中一共展示了ops.reframe_box_masks_to_image_masks方法的5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: testZeroImageOnEmptyMask

# 需要導入模塊: from object_detection.utils import ops [as 別名]
# 或者: from object_detection.utils.ops import reframe_box_masks_to_image_masks [as 別名]
def testZeroImageOnEmptyMask(self):
    box_masks = tf.constant([[[0, 0],
                              [0, 0]]], dtype=tf.float32)
    boxes = tf.constant([[0.0, 0.0, 1.0, 1.0]], dtype=tf.float32)
    image_masks = ops.reframe_box_masks_to_image_masks(box_masks, boxes,
                                                       image_height=4,
                                                       image_width=4)
    np_expected_image_masks = np.array([[[0, 0, 0, 0],
                                         [0, 0, 0, 0],
                                         [0, 0, 0, 0],
                                         [0, 0, 0, 0]]], dtype=np.float32)
    with self.test_session() as sess:
      np_image_masks = sess.run(image_masks)
      self.assertAllClose(np_image_masks, np_expected_image_masks) 
開發者ID:ringringyi,項目名稱:DOTA_models,代碼行數:16,代碼來源:ops_test.py

示例2: testMaskIsCenteredInImageWhenBoxIsCentered

# 需要導入模塊: from object_detection.utils import ops [as 別名]
# 或者: from object_detection.utils.ops import reframe_box_masks_to_image_masks [as 別名]
def testMaskIsCenteredInImageWhenBoxIsCentered(self):
    box_masks = tf.constant([[[1, 1],
                              [1, 1]]], dtype=tf.float32)
    boxes = tf.constant([[0.25, 0.25, 0.75, 0.75]], dtype=tf.float32)
    image_masks = ops.reframe_box_masks_to_image_masks(box_masks, boxes,
                                                       image_height=4,
                                                       image_width=4)
    np_expected_image_masks = np.array([[[0, 0, 0, 0],
                                         [0, 1, 1, 0],
                                         [0, 1, 1, 0],
                                         [0, 0, 0, 0]]], dtype=np.float32)
    with self.test_session() as sess:
      np_image_masks = sess.run(image_masks)
      self.assertAllClose(np_image_masks, np_expected_image_masks) 
開發者ID:ringringyi,項目名稱:DOTA_models,代碼行數:16,代碼來源:ops_test.py

示例3: testMaskOffCenterRemainsOffCenterInImage

# 需要導入模塊: from object_detection.utils import ops [as 別名]
# 或者: from object_detection.utils.ops import reframe_box_masks_to_image_masks [as 別名]
def testMaskOffCenterRemainsOffCenterInImage(self):
    box_masks = tf.constant([[[1, 0],
                              [0, 1]]], dtype=tf.float32)
    boxes = tf.constant([[0.25, 0.5, 0.75, 1.0]], dtype=tf.float32)
    image_masks = ops.reframe_box_masks_to_image_masks(box_masks, boxes,
                                                       image_height=4,
                                                       image_width=4)
    np_expected_image_masks = np.array([[[0, 0, 0, 0],
                                         [0, 0, 0.6111111, 0.16666669],
                                         [0, 0, 0.3888889, 0.83333337],
                                         [0, 0, 0, 0]]], dtype=np.float32)
    with self.test_session() as sess:
      np_image_masks = sess.run(image_masks)
      self.assertAllClose(np_image_masks, np_expected_image_masks) 
開發者ID:ringringyi,項目名稱:DOTA_models,代碼行數:16,代碼來源:ops_test.py

示例4: _resize_detection_masks

# 需要導入模塊: from object_detection.utils import ops [as 別名]
# 或者: from object_detection.utils.ops import reframe_box_masks_to_image_masks [as 別名]
def _resize_detection_masks(args):
  detection_boxes, detection_masks, image_shape = args
  detection_masks_reframed = ops.reframe_box_masks_to_image_masks(
      detection_masks, detection_boxes, image_shape[0], image_shape[1])
  return tf.cast(tf.greater(detection_masks_reframed, 0.5), tf.uint8) 
開發者ID:ahmetozlu,項目名稱:vehicle_counting_tensorflow,代碼行數:7,代碼來源:eval_util.py

示例5: testZeroBoxMasks

# 需要導入模塊: from object_detection.utils import ops [as 別名]
# 或者: from object_detection.utils.ops import reframe_box_masks_to_image_masks [as 別名]
def testZeroBoxMasks(self):
    box_masks = tf.zeros([0, 3, 3], dtype=tf.float32)
    boxes = tf.zeros([0, 4], dtype=tf.float32)
    image_masks = ops.reframe_box_masks_to_image_masks(box_masks, boxes,
                                                       image_height=4,
                                                       image_width=4)
    with self.test_session() as sess:
      np_image_masks = sess.run(image_masks)
      self.assertAllEqual(np_image_masks.shape, np.array([0, 4, 4])) 
開發者ID:ahmetozlu,項目名稱:vehicle_counting_tensorflow,代碼行數:11,代碼來源:ops_test.py


注:本文中的object_detection.utils.ops.reframe_box_masks_to_image_masks方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台,相關代碼片段篩選自各路編程大神貢獻的開源項目,源碼版權歸原作者所有,傳播和使用請參考對應項目的License;未經允許,請勿轉載。