This easy-to-use library is a data transformer maybe useful in Object Detection tasks. It splits images and their bounding box annotations into tiles, both into specific sizes and into any arbitrary number of equal parts. It can also resize them, both by specific sizes and by a resizing/scaling factor. Currently only supports PASCAL VOC format. COCO format support will be added soon.
Don't forget to tag @acl21 in your comment, otherwise they may not be notified.