[TFLite object detection post-process] Adding box clipping

Prerequisites

1. The entire URL of the file you are using

https://github.com/tensorflow/models/blob/master/research/object_detection/export_tflite_graph_lib_tf2.py

2. Describe the feature you request

I would like to request adding an option for box clipping to the tflite custom post-processing op. The box clipping operation after box decode is standard in the post-processing pipeline in object detection. The lack of box clipping causes a degradation in performance when using benchmarks such as COCO (since the ground truth boxes are always clipped to the image size). Thank you very much!