google cloud visionで顔検出チュートリアル、AttributeError: 'str' object has no attribute 'batch_annotate_images'

google cloud visionの顔検出のチュートリアル(https://cloud.google.com/vision/docs/face-tutorial)を試しているのですが、表題の通りこのようなエラーでつまづいてます。

Traceback (most recent call last):
  File "google_face_detect.py", line 79, in <module>
    main(args.input_image, args.output, args.max_results)
  File "google_face_detect.py", line 55, in main
    faces = detect_face(image, max_results)
  File "google_face_detect.py", line 26, in detect_face
    return client.face_detection(image=image).face_annotations
  File "/Users/kentasuhara/.pyenv/versions/anaconda3-5.0.0/lib/python3.6/site-packages/google/cloud/vision_helpers/decorators.py", line 111, in inner
    response = self.annotate_image(request, retry=retry, timeout=timeout)
  File "/Users/kentasuhara/.pyenv/versions/anaconda3-5.0.0/lib/python3.6/site-packages/google/cloud/vision_helpers/__init__.py", line 67, in annotate_image
    r = self.batch_annotate_images([request], retry=retry, timeout=timeout)
  File "/Users/kentasuhara/.pyenv/versions/anaconda3-5.0.0/lib/python3.6/site-packages/google/cloud/vision_v1/gapic/image_annotator_client.py", line 209, in batch_annotate_images
    self.transport.batch_annotate_images,
AttributeError: 'str' object has no attribute 'batch_annotate_images'

どこがstrになっていてどう直せばいいのでしょうか？

コードは以下の通りで、githubのコードをほぼそのままコピペしています。
またターミナルで実行しているコードは $python google_face_detect.py(ファイル名) 画像の絶対パス　です。

import argparse

# [START vision_face_detection_tutorial_imports]
from google.cloud import vision
from google.cloud.vision import types
from PIL import Image, ImageDraw
# [END vision_face_detection_tutorial_imports]

GOOGLE_APPLICATION_CREDENTIALS="絶対パス"

# [START vision_face_detection_tutorial_send_request]
def detect_face(face_file, max_results=4):
    """Uses the Vision API to detect faces in the given file.
    Args:
        face_file: A file-like object containing an image with faces.
    Returns:
        An array of Face objects with information about the picture.
    """
    # [START vision_face_detection_tutorial_client]
    client = vision.ImageAnnotatorClient(GOOGLE_APPLICATION_CREDENTIALS)
    # [END vision_face_detection_tutorial_client]

    content = face_file.read()
    image = types.Image(content=content)

    return client.face_detection(image=image).face_annotations
# [END vision_face_detection_tutorial_send_request]


# [START vision_face_detection_tutorial_process_response]
def highlight_faces(image, faces, output_filename):
    """Draws a polygon around the faces, then saves to output_filename.
    Args:
      image: a file containing the image with the faces.
      faces: a list of faces found in the file. This should be in the format
          returned by the Vision API.
      output_filename: the name of the image file to be created, where the
          faces have polygons drawn around them.
    """
    im = Image.open(image)
    draw = ImageDraw.Draw(im)

    for face in faces:
        box = [(vertex.x, vertex.y)
               for vertex in face.bounding_poly.vertices]
        draw.line(box + [box[0]], width=5, fill='#00ff00')

    im.save(output_filename)
# [END vision_face_detection_tutorial_process_response]


# [START vision_face_detection_tutorial_run_application]
def main(input_filename, output_filename, max_results):
    with open(input_filename, 'rb') as image:
        faces = detect_face(image, max_results)
        print('Found {} face{}'.format(
            len(faces), '' if len(faces) == 1 else 's'))

        print('Writing to file {}'.format(output_filename))
        # Reset the file pointer, so we can read the file again
        image.seek(0)
        highlight_faces(image, faces, output_filename)
# [END vision_face_detection_tutorial_run_application]


if __name__ == '__main__':
    parser = argparse.ArgumentParser(
        description='Detects faces in the given image.')
    parser.add_argument(
        'input_image', help='the image you\'d like to detect faces in.')
    parser.add_argument(
        '--out', dest='output', default='out.jpg',
        help='the name of the output file.')
    parser.add_argument(
        '--max-results', dest='max_results', default=4,
        help='the max results of face detection.')
    args = parser.parse_args()

    main(args.input_image, args.output, args.max_results)

よろしくお願いします。