Python preprocessor.resize_to_range方法代码示例

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRange(self):
    """Tests image resizing, checking output sizes."""
    in_shape_list = [[60, 40, 3], [15, 30, 3], [15, 50, 3]]
    min_dim = 50
    max_dim = 100
    expected_shape_list = [[75, 50, 3], [50, 100, 3], [30, 100, 3]]

    for in_shape, expected_shape in zip(in_shape_list, expected_shape_list):
      in_image = tf.random_uniform(in_shape)
      out_image = preprocessor.resize_to_range(
          in_image, min_dimension=min_dim, max_dimension=max_dim)
      out_image_shape = tf.shape(out_image)

      with self.test_session() as sess:
        out_image_shape = sess.run(out_image_shape)
        self.assertAllEqual(out_image_shape, expected_shape) 

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRangeSameMinMax(self):
    """Tests image resizing, checking output sizes."""
    in_shape_list = [[312, 312, 3], [299, 299, 3]]
    min_dim = 320
    max_dim = 320
    expected_shape_list = [[320, 320, 3], [320, 320, 3]]

    for in_shape, expected_shape in zip(in_shape_list, expected_shape_list):
      in_image = tf.random_uniform(in_shape)
      out_image = preprocessor.resize_to_range(
          in_image, min_dimension=min_dim, max_dimension=max_dim)
      out_image_shape = tf.shape(out_image)

      with self.test_session() as sess:
        out_image_shape = sess.run(out_image_shape)
        self.assertAllEqual(out_image_shape, expected_shape) 

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRangeWithDynamicSpatialShape(self):
    """Tests image resizing, checking output sizes."""
    in_shape_list = [[60, 40, 3], [15, 30, 3], [15, 50, 3]]
    min_dim = 50
    max_dim = 100
    expected_shape_list = [[75, 50, 3], [50, 100, 3], [30, 100, 3]]

    for in_shape, expected_shape in zip(in_shape_list, expected_shape_list):
      in_image = tf.placeholder(tf.float32, shape=(None, None, 3))
      out_image, _ = preprocessor.resize_to_range(
          in_image, min_dimension=min_dim, max_dimension=max_dim)
      out_image_shape = tf.shape(out_image)
      with self.test_session() as sess:
        out_image_shape = sess.run(out_image_shape,
                                   feed_dict={in_image:
                                              np.random.randn(*in_shape)})
        self.assertAllEqual(out_image_shape, expected_shape) 

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRangeWithPadToMaxDimensionReturnsCorrectShapes(self):
    in_shape_list = [[60, 40, 3], [15, 30, 3], [15, 50, 3]]
    min_dim = 50
    max_dim = 100
    expected_shape_list = [[100, 100, 3], [100, 100, 3], [100, 100, 3]]

    for in_shape, expected_shape in zip(in_shape_list, expected_shape_list):
      in_image = tf.placeholder(tf.float32, shape=(None, None, 3))
      out_image, _ = preprocessor.resize_to_range(
          in_image,
          min_dimension=min_dim,
          max_dimension=max_dim,
          pad_to_max_dimension=True)
      self.assertAllEqual(out_image.shape.as_list(), expected_shape)
      out_image_shape = tf.shape(out_image)
      with self.test_session() as sess:
        out_image_shape = sess.run(
            out_image_shape, feed_dict={in_image: np.random.randn(*in_shape)})
        self.assertAllEqual(out_image_shape, expected_shape) 

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRangeWithPadToMaxDimensionReturnsCorrectTensor(self):
    in_image_np = np.array([[[0, 1, 2]]], np.float32)
    ex_image_np = np.array(
        [[[0, 1, 2], [123.68, 116.779, 103.939]],
         [[123.68, 116.779, 103.939], [123.68, 116.779, 103.939]]], np.float32)
    min_dim = 1
    max_dim = 2

    in_image = tf.placeholder(tf.float32, shape=(None, None, 3))
    out_image, _ = preprocessor.resize_to_range(
        in_image,
        min_dimension=min_dim,
        max_dimension=max_dim,
        pad_to_max_dimension=True,
        per_channel_pad_value=(123.68, 116.779, 103.939))

    with self.test_session() as sess:
      out_image_np = sess.run(out_image, feed_dict={in_image: in_image_np})
      self.assertAllClose(ex_image_np, out_image_np) 

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRangeWithMasksPreservesStaticSpatialShape(self):
    """Tests image resizing, checking output sizes."""
    in_image_shape_list = [[60, 40, 3], [15, 30, 3]]
    in_masks_shape_list = [[15, 60, 40], [10, 15, 30]]
    min_dim = 50
    max_dim = 100
    expected_image_shape_list = [[75, 50, 3], [50, 100, 3]]
    expected_masks_shape_list = [[15, 75, 50], [10, 50, 100]]

    for (in_image_shape, expected_image_shape, in_masks_shape,
         expected_mask_shape) in zip(in_image_shape_list,
                                     expected_image_shape_list,
                                     in_masks_shape_list,
                                     expected_masks_shape_list):
      in_image = tf.random_uniform(in_image_shape)
      in_masks = tf.random_uniform(in_masks_shape)
      out_image, out_masks, _ = preprocessor.resize_to_range(
          in_image, in_masks, min_dimension=min_dim, max_dimension=max_dim)
      self.assertAllEqual(out_masks.get_shape().as_list(), expected_mask_shape)
      self.assertAllEqual(out_image.get_shape().as_list(), expected_image_shape) 

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRangeSameMinMax(self):
    """Tests image resizing, checking output sizes."""
    in_shape_list = [[312, 312, 3], [299, 299, 3]]
    min_dim = 320
    max_dim = 320
    expected_shape_list = [[320, 320, 3], [320, 320, 3]]

    for in_shape, expected_shape in zip(in_shape_list, expected_shape_list):
      in_image = tf.random_uniform(in_shape)
      out_image, _ = preprocessor.resize_to_range(
          in_image, min_dimension=min_dim, max_dimension=max_dim)
      out_image_shape = tf.shape(out_image)

      with self.test_session() as sess:
        out_image_shape = sess.run(out_image_shape)
        self.assertAllEqual(out_image_shape, expected_shape) 

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRangeWithDynamicSpatialShape(self):
    """Tests image resizing, checking output sizes."""
    in_shape_list = [[60, 40, 3], [15, 30, 3], [15, 50, 3]]
    min_dim = 50
    max_dim = 100
    expected_shape_list = [[75, 50, 3], [50, 100, 3], [30, 100, 3]]

    for in_shape, expected_shape in zip(in_shape_list, expected_shape_list):
      in_image = tf.placeholder(tf.float32, shape=(None, None, 3))
      out_image = preprocessor.resize_to_range(
          in_image, min_dimension=min_dim, max_dimension=max_dim)
      out_image_shape = tf.shape(out_image)
      with self.test_session() as sess:
        out_image_shape = sess.run(out_image_shape,
                                   feed_dict={in_image:
                                              np.random.randn(*in_shape)})
        self.assertAllEqual(out_image_shape, expected_shape) 

# 需要导入模块: from object_detection.core import preprocessor [as 别名]
# 或者: from object_detection.core.preprocessor import resize_to_range [as 别名]
def testResizeToRangeWithMasksPreservesStaticSpatialShape(self):
    """Tests image resizing, checking output sizes."""
    in_image_shape_list = [[60, 40, 3], [15, 30, 3]]
    in_masks_shape_list = [[15, 60, 40], [10, 15, 30]]
    min_dim = 50
    max_dim = 100
    expected_image_shape_list = [[75, 50, 3], [50, 100, 3]]
    expected_masks_shape_list = [[15, 75, 50], [10, 50, 100]]

    for (in_image_shape, expected_image_shape, in_masks_shape,
         expected_mask_shape) in zip(in_image_shape_list,
                                     expected_image_shape_list,
                                     in_masks_shape_list,
                                     expected_masks_shape_list):
      in_image = tf.random_uniform(in_image_shape)
      in_masks = tf.random_uniform(in_masks_shape)
      out_image, out_masks = preprocessor.resize_to_range(
          in_image, in_masks, min_dimension=min_dim, max_dimension=max_dim)
      self.assertAllEqual(out_masks.get_shape().as_list(), expected_mask_shape)
      self.assertAllEqual(out_image.get_shape().as_list(), expected_image_shape)