def parse_instance()

in utils_cv/detection/references/anno_coco2voc.py [0:0]

• 34 lines of code
• 15 McCabe index (conditional complexity)

def parse_instance(content, outdir, download_images = False):
    categories = {d['id']: d['name'] for d in content['categories']}

    # EDITED - make sure image_id is of type int (and not of type string)
    for i in range(len(content['annotations'])):
        content['annotations'][i]['image_id'] = int(content['annotations'][i]['image_id'])

    # EDITED - save all annotation .xml files into same sub-directory
    anno_dir = os.path.join(outdir, "annotations")
    if not os.path.exists(anno_dir):
        os.makedirs(anno_dir)

    # EDITED - download images
    if download_images:
        im_dir = os.path.join(outdir, "images")
        if not os.path.exists(im_dir):
            os.makedirs(im_dir)

        for index, obj in enumerate(content['images']):
            print(f"Downloading image {index} of {len(content['images'])} from: {obj['coco_url']}")

            # Update 'filename' field to be a (local) filename and not a url
            im_local_filename = os.path.splitext(os.path.basename(obj['file_name']))[0] + ".jpg"
            obj['file_name'] = im_local_filename

            # download image
            dst_path = os.path.join(im_dir, im_local_filename)
            urllib.request.urlretrieve(obj['coco_url'], dst_path)

    # merge images and annotations: id in images vs image_id in annotations
    merged_info_list = list(map(cytoolz.merge, cytoolz.join('id', content['images'], 'image_id', content['annotations'])))
    
    # convert category id to name
    for instance in merged_info_list:
        assert 'category_id' in instance, f"WARNING: annotation error: image {instance['file_name']} has a rectangle without a 'category_id' field."
        instance['category_id'] = categories[instance['category_id']]

    # group by filename to pool all bbox in same file
    img_filenames = {}
    names_groups = cytoolz.groupby('file_name', merged_info_list).items()
    for index, (name, groups) in enumerate(names_groups):
        print(f"Converting annotations for image {index} of {len(names_groups)}: {name}")
        assert not name.lower().startswith(("http:","https:")), "Image seems to be a url rather than local. Need to set 'download_images' = False"

        anno_tree = instance2xml_base(groups[0], download_images)
        # if one file have multiple different objects, save it in each category sub-directory
        filenames = []
        for group in groups:
            filename = os.path.splitext(name)[0] + ".xml"

            # EDITED - save all annotations in single folder, rather than separate folders for each object 
            #filenames.append(os.path.join(outdir, re.sub(" ", "_", group['category_id']), filename)) 
            filenames.append(os.path.join(anno_dir, filename))

            anno_tree.append(instance2xml_bbox(group, bbox_type='xyxy'))

        for filename in filenames:
            etree.ElementTree(anno_tree).write(filename, pretty_print=True)