I think it will be converted internally if you pass it in this format.
The image_processor expects the annotations to be in the following format: {'image_id': int, 'annotations': list[Dict]}, where each dictionary is a COCO object annotation.
I have a COCO database in my disk (with a JSON in the annotations folder that contains image directions) and I would like to load it in HF dataset in orther to use CV models.
Is there a function that allows that?
"""
height, width = image_size
height_scale = max_height / height
width_scale = max_width / width
min_scale = min(height_scale, width_scale)
new_height = int(height * min_scale)
new_width = int(width * min_scale)
return new_height, new_width
def is_valid_annotation_coco_detection(annotation: dict[str, Union[list, tuple]]) -> bool:
if (
isinstance(annotation, dict)
and "image_id" in annotation
and "annotations" in annotation
and isinstance(annotation["annotations"], (list, tuple))
and (
# an image can have no annotations
len(annotation["annotations"]) == 0 or isinstance(annotation["annotations"][0], dict)
)
):