Disabling the return of particular outputs from TF Serving

Prerequisites

Please answer the following question for yourself before submitting an issue.

• [DONE] I checked to make sure that this feature has not been requested already.

1. The entire URL of the file you are using

https://github.com/tensorflow/models/blob/master/research/object_detection/configs/tf2/mask_rcnn_inception_resnet_v2_1024x1024_coco17_gpu-8.config

2. Describe the feature you request

I want to be able to disable certain outputs from the model. When hosted with TF Serving the model returns 5GB of data. The mask_predictions output has a size of 3669.36MB and the box_classifier_features output has a size of 1156.30MB. It is unreasonable to transfer this much data for every inference made with the model.

3. Additional context

4. Are you willing to contribute it? (Yes or No)

No