Python dataset_util.bytes_feature方法代码示例

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def create_mock_tfrecord():
  pil_image = Image.fromarray(np.array([[[123, 0, 0]]], dtype=np.uint8), 'RGB')
  image_output_stream = StringIO.StringIO()
  pil_image.save(image_output_stream, format='png')
  encoded_image = image_output_stream.getvalue()

  feature_map = {
      'test_field':
          dataset_util.float_list_feature([1, 2, 3, 4]),
      standard_fields.TfExampleFields.image_encoded:
          dataset_util.bytes_feature(encoded_image),
  }

  tf_example = tf.train.Example(features=tf.train.Features(feature=feature_map))
  with tf.python_io.TFRecordWriter(get_mock_tfrecord_path()) as writer:
    writer.write(tf_example.SerializeToString()) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeImageKeyAndFilename(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded': dataset_util.bytes_feature(encoded_jpeg),
                'image/key/sha256': dataset_util.bytes_feature('abc'),
                'image/filename': dataset_util.bytes_feature('filename')
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder()
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)

    self.assertEqual('abc', tensor_dict[fields.InputDataFields.key])
    self.assertEqual('filename', tensor_dict[fields.InputDataFields.filename]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeObjectArea(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    object_area = [100., 174.]
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded':
                    dataset_util.bytes_feature(encoded_jpeg),
                'image/format':
                    dataset_util.bytes_feature('jpeg'),
                'image/object/area':
                    dataset_util.float_list_feature(object_area),
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder()
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_area]
                         .get_shape().as_list()), [2])
    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)

    self.assertAllEqual(object_area,
                        tensor_dict[fields.InputDataFields.groundtruth_area]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeObjectWeight(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    object_weights = [0.75, 1.0]
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded':
                    dataset_util.bytes_feature(encoded_jpeg),
                'image/format':
                    dataset_util.bytes_feature('jpeg'),
                'image/object/weight':
                    dataset_util.float_list_feature(object_weights),
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder()
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_weights]
                         .get_shape().as_list()), [None])
    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)

    self.assertAllEqual(object_weights,
                        tensor_dict[fields.InputDataFields.groundtruth_weights]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def create_tf_record(self):
    path = os.path.join(self.get_temp_dir(), 'tfrecord')
    writer = tf.python_io.TFRecordWriter(path)

    image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
    flat_mask = (4 * 5) * [1.0]
    with self.test_session():
      encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval()
    example = tf.train.Example(features=tf.train.Features(feature={
        'image/encoded': dataset_util.bytes_feature(encoded_jpeg),
        'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
        'image/height': dataset_util.int64_feature(4),
        'image/width': dataset_util.int64_feature(5),
        'image/object/bbox/xmin': dataset_util.float_list_feature([0.0]),
        'image/object/bbox/xmax': dataset_util.float_list_feature([1.0]),
        'image/object/bbox/ymin': dataset_util.float_list_feature([0.0]),
        'image/object/bbox/ymax': dataset_util.float_list_feature([1.0]),
        'image/object/class/label': dataset_util.int64_list_feature([2]),
        'image/object/mask': dataset_util.float_list_feature(flat_mask),
    }))
    writer.write(example.SerializeToString())
    writer.close()

    return path 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeAdditionalChannels(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)

    additional_channel_tensor = np.random.randint(
        256, size=(4, 5, 1)).astype(np.uint8)
    encoded_additional_channel = self._EncodeImage(additional_channel_tensor)
    decoded_additional_channel = self._DecodeImage(encoded_additional_channel)

    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded':
                    dataset_util.bytes_feature(encoded_jpeg),
                'image/additional_channels/encoded':
                    dataset_util.bytes_list_feature(
                        [encoded_additional_channel] * 2),
                'image/format':
                    dataset_util.bytes_feature('jpeg'),
                'image/source_id':
                    dataset_util.bytes_feature('image_id'),
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder(
        num_additional_channels=2)
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)
      self.assertAllEqual(
          np.concatenate([decoded_additional_channel] * 2, axis=2),
          tensor_dict[fields.InputDataFields.image_additional_channels]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeJpegImage(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    decoded_jpeg = self._DecodeImage(encoded_jpeg)
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded': dataset_util.bytes_feature(encoded_jpeg),
                'image/format': dataset_util.bytes_feature('jpeg'),
                'image/source_id': dataset_util.bytes_feature('image_id'),
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder()
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    self.assertAllEqual((tensor_dict[fields.InputDataFields.image].
                         get_shape().as_list()), [None, None, 3])
    self.assertAllEqual((tensor_dict[fields.InputDataFields.
                                     original_image_spatial_shape].
                         get_shape().as_list()), [2])
    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)

    self.assertAllEqual(decoded_jpeg, tensor_dict[fields.InputDataFields.image])
    self.assertAllEqual([4, 5], tensor_dict[fields.InputDataFields.
                                            original_image_spatial_shape])
    self.assertEqual('image_id', tensor_dict[fields.InputDataFields.source_id]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodePngImage(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_png = self._EncodeImage(image_tensor, encoding_type='png')
    decoded_png = self._DecodeImage(encoded_png, encoding_type='png')
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded': dataset_util.bytes_feature(encoded_png),
                'image/format': dataset_util.bytes_feature('png'),
                'image/source_id': dataset_util.bytes_feature('image_id')
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder()
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    self.assertAllEqual((tensor_dict[fields.InputDataFields.image].
                         get_shape().as_list()), [None, None, 3])
    self.assertAllEqual((tensor_dict[fields.InputDataFields.
                                     original_image_spatial_shape].
                         get_shape().as_list()), [2])
    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)

    self.assertAllEqual(decoded_png, tensor_dict[fields.InputDataFields.image])
    self.assertAllEqual([4, 5], tensor_dict[fields.InputDataFields.
                                            original_image_spatial_shape])
    self.assertEqual('image_id', tensor_dict[fields.InputDataFields.source_id]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeEmptyPngInstanceMasks(self):
    image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    encoded_masks = []
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded':
                    dataset_util.bytes_feature(encoded_jpeg),
                'image/format':
                    dataset_util.bytes_feature('jpeg'),
                'image/object/mask':
                    dataset_util.bytes_list_feature(encoded_masks),
                'image/height':
                    dataset_util.int64_feature(10),
                'image/width':
                    dataset_util.int64_feature(10),
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder(
        load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)
      self.assertAllEqual(
          tensor_dict[fields.InputDataFields.groundtruth_instance_masks].shape,
          [0, 10, 10]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeBoundingBox(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    bbox_ymins = [0.0, 4.0]
    bbox_xmins = [1.0, 5.0]
    bbox_ymaxs = [2.0, 6.0]
    bbox_xmaxs = [3.0, 7.0]
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded':
                    dataset_util.bytes_feature(encoded_jpeg),
                'image/format':
                    dataset_util.bytes_feature('jpeg'),
                'image/object/bbox/ymin':
                    dataset_util.float_list_feature(bbox_ymins),
                'image/object/bbox/xmin':
                    dataset_util.float_list_feature(bbox_xmins),
                'image/object/bbox/ymax':
                    dataset_util.float_list_feature(bbox_ymaxs),
                'image/object/bbox/xmax':
                    dataset_util.float_list_feature(bbox_xmaxs),
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder()
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_boxes]
                         .get_shape().as_list()), [None, 4])
    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)

    expected_boxes = np.vstack([bbox_ymins, bbox_xmins, bbox_ymaxs,
                                bbox_xmaxs]).transpose()
    self.assertAllEqual(expected_boxes,
                        tensor_dict[fields.InputDataFields.groundtruth_boxes]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeDefaultGroundtruthWeights(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    bbox_ymins = [0.0, 4.0]
    bbox_xmins = [1.0, 5.0]
    bbox_ymaxs = [2.0, 6.0]
    bbox_xmaxs = [3.0, 7.0]
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded':
                    dataset_util.bytes_feature(encoded_jpeg),
                'image/format':
                    dataset_util.bytes_feature('jpeg'),
                'image/object/bbox/ymin':
                    dataset_util.float_list_feature(bbox_ymins),
                'image/object/bbox/xmin':
                    dataset_util.float_list_feature(bbox_xmins),
                'image/object/bbox/ymax':
                    dataset_util.float_list_feature(bbox_ymaxs),
                'image/object/bbox/xmax':
                    dataset_util.float_list_feature(bbox_xmaxs),
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder()
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_boxes]
                         .get_shape().as_list()), [None, 4])

    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)

    self.assertAllClose(tensor_dict[fields.InputDataFields.groundtruth_weights],
                        np.ones(2, dtype=np.float32)) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeObjectLabel(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    bbox_classes = [0, 1]
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded':
                    dataset_util.bytes_feature(encoded_jpeg),
                'image/format':
                    dataset_util.bytes_feature('jpeg'),
                'image/object/class/label':
                    dataset_util.int64_list_feature(bbox_classes),
            })).SerializeToString()

    example_decoder = tf_example_decoder.TfExampleDecoder()
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
                         .get_shape().as_list()), [2])

    with self.test_session() as sess:
      tensor_dict = sess.run(tensor_dict)

    self.assertAllEqual(bbox_classes,
                        tensor_dict[fields.InputDataFields.groundtruth_classes]) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import bytes_feature [as 别名]
def testDecodeObjectLabelUnrecognizedName(self):
    image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
    encoded_jpeg = self._EncodeImage(image_tensor)
    bbox_classes_text = ['cat', 'cheetah']
    example = tf.train.Example(
        features=tf.train.Features(
            feature={
                'image/encoded':
                    dataset_util.bytes_feature(encoded_jpeg),
                'image/format':
                    dataset_util.bytes_feature('jpeg'),
                'image/object/class/text':
                    dataset_util.bytes_list_feature(bbox_classes_text),
            })).SerializeToString()

    label_map_string = """
      item {
        id:2
        name:'cat'
      }
      item {
        id:1
        name:'dog'
      }
    """
    label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
    with tf.gfile.Open(label_map_path, 'wb') as f:
      f.write(label_map_string)
    example_decoder = tf_example_decoder.TfExampleDecoder(
        label_map_proto_file=label_map_path)
    tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))

    self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
                         .get_shape().as_list()), [None])

    with self.test_session() as sess:
      sess.run(tf.tables_initializer())
      tensor_dict = sess.run(tensor_dict)

    self.assertAllEqual([2, -1],
                        tensor_dict[fields.InputDataFields.groundtruth_classes])