Error reading B&W object

[LorenzG]

Hello

I'm getting the following error when trying to read a B&W image:

ValueError                                Traceback (most recent call last)
<ipython-input-11-d250c4835c35> in <module>()
----> 1 target,_ = generator.next()
      2 
      3 target_bounding_boxes, target_categories, target_images, target_masks, target_metadata = target
      4 
      5 target_bounding_boxes = numpy.squeeze(target_bounding_boxes)

~\Anaconda3\envs\tensorflow\lib\site-packages\keras_rcnn\preprocessing\_object_detection.py in next(self)
     87             selection = next(self.index_generator)
     88 
---> 89         return self._get_batches_of_transformed_samples(selection)
     90 
     91     def find_scale(self, image):

~\Anaconda3\envs\tensorflow\lib\site-packages\keras_rcnn\preprocessing\_object_detection.py in _get_batches_of_transformed_samples(self, selection)
    142         while True:
    143             try:
--> 144                 x = self._transform_samples(batch_index, image_index)
    145             except BoundingBoxException:
    146                 continue

~\Anaconda3\envs\tensorflow\lib\site-packages\keras_rcnn\preprocessing\_object_detection.py in _transform_samples(self, batch_index, image_index)
    197         dimensions = dimensions.astype(numpy.float16)
    198 
--> 199         scale = self.find_scale(image)
    200 
    201         dimensions *= scale

~\Anaconda3\envs\tensorflow\lib\site-packages\keras_rcnn\preprocessing\_object_detection.py in find_scale(self, image)
     90 
     91     def find_scale(self, image):
---> 92         r, c, _ = image.shape
     93 
     94         scale = self.minimum / numpy.minimum(r, c)

ValueError: not enough values to unpack (expected 3, got 2)

This is my code:

categories = {"sick": 1}

generator = preprocessing.ObjectDetectionGenerator()

generator = generator.flow_from_dictionary(
    dictionary=training_dictionary,
    categories=categories,
    target_size=(224, 224),
    color_mode='grayscale'
)

target,_ = generator.next()

and I'm using this image:
https://drive.google.com/open?id=1IufZFg8HmwwfIuzy4v5xkGKG3QTlv-WI