當前位置: 首頁>>代碼示例>>Python>>正文


Python preprocessor.random_resize_method方法代碼示例

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


在下文中一共展示了preprocessor.random_resize_method方法的3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: testRandomResizeMethod

# 需要導入模塊: from object_detection.core import preprocessor [as 別名]
# 或者: from object_detection.core.preprocessor import random_resize_method [as 別名]
def testRandomResizeMethod(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_resize_method, {
        'target_size': (75, 150)
    }))
    images = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images}
    resized_tensor_dict = preprocessor.preprocess(tensor_dict,
                                                  preprocessing_options)
    resized_images = resized_tensor_dict[fields.InputDataFields.image]
    resized_images_shape = tf.shape(resized_images)
    expected_images_shape = tf.constant([1, 75, 150, 3], dtype=tf.int32)

    with self.test_session() as sess:
      (expected_images_shape_, resized_images_shape_) = sess.run(
          [expected_images_shape, resized_images_shape])
      self.assertAllEqual(expected_images_shape_,
                          resized_images_shape_) 
開發者ID:ringringyi,項目名稱:DOTA_models,代碼行數:26,代碼來源:preprocessor_test.py

示例2: testRandomResizeMethod

# 需要導入模塊: from object_detection.core import preprocessor [as 別名]
# 或者: from object_detection.core.preprocessor import random_resize_method [as 別名]
def testRandomResizeMethod(self):
    def graph_fn():
      preprocessing_options = []
      preprocessing_options.append((preprocessor.normalize_image, {
          'original_minval': 0,
          'original_maxval': 255,
          'target_minval': 0,
          'target_maxval': 1
      }))
      preprocessing_options.append((preprocessor.random_resize_method, {
          'target_size': (75, 150)
      }))
      images = self.createTestImages()
      tensor_dict = {fields.InputDataFields.image: images}
      resized_tensor_dict = preprocessor.preprocess(tensor_dict,
                                                    preprocessing_options)
      resized_images = resized_tensor_dict[fields.InputDataFields.image]
      resized_images_shape = tf.shape(resized_images)
      expected_images_shape = tf.constant([1, 75, 150, 3], dtype=tf.int32)
      return [expected_images_shape, resized_images_shape]
    (expected_images_shape_, resized_images_shape_) = self.execute_cpu(graph_fn,
                                                                       [])
    self.assertAllEqual(expected_images_shape_,
                        resized_images_shape_) 
開發者ID:tensorflow,項目名稱:models,代碼行數:26,代碼來源:preprocessor_test.py

示例3: test_build_random_resize_method

# 需要導入模塊: from object_detection.core import preprocessor [as 別名]
# 或者: from object_detection.core.preprocessor import random_resize_method [as 別名]
def test_build_random_resize_method(self):
    preprocessor_text_proto = """
    random_resize_method {
      target_height: 75
      target_width: 100
    }
    """
    preprocessor_proto = preprocessor_pb2.PreprocessingStep()
    text_format.Merge(preprocessor_text_proto, preprocessor_proto)
    function, args = preprocessor_builder.build(preprocessor_proto)
    self.assertEqual(function, preprocessor.random_resize_method)
    self.assert_dictionary_close(args, {'target_size': [75, 100]}) 
開發者ID:ringringyi,項目名稱:DOTA_models,代碼行數:14,代碼來源:preprocessor_builder_test.py


注:本文中的object_detection.core.preprocessor.random_resize_method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。