Mask-Rcnn transfer learning example

Any chance of getting a simple example (even just ad hoc ) on how to train mask rcnn via transfer learning on a custom Coco formatted dataset ?

We are currently evaluating if we need to write our main application in python because of this requirement or if we can switch to JVM/Kotlin ( which we would prefer ) and I would really like to do a small POC on this.

The issue names no files, tests, or entry points. Start by locating the existing Mask R-CNN and COCO-related examples, then define a small transfer-learning example for a custom COCO-formatted dataset; done means the example supports the requested JVM/Kotlin proof of concept.

Written by the indexing model from the issue text.