Models: How to retrain models of Tensorflow API by adding new classes to existing model?

[saikishor]

I would like to know how to retrain a pre-trained model available from the above repository, by adding new classes to the model.
For example, COCO dataset trained model has 90 classes, I would like to add 1 or 2 classes to the existing one and get one 92 class object detection model as a result.

Running Locally is provided by the repository but it is totally replacing those pre-trained classes with newly trained classes, there only train and eval are mentioned.

So, is there any other way to retrain the model and get 92 classes as a result?

[asimshankar]

This question is better asked on StackOverflow since it is not a bug or feature request. There is also a larger community that reads questions there. Thanks!

[Vayrex]

Hi, I'm having similar issue like saikishor, here is link to his question, but there are not good answers.
https://stackoverflow.com/questions/46572573/how-to-get-existing-model-to-recognize-additional-classes#
Can you tell, is that possible ?

[Vayrex]

If asking about such feature, we need to know that it is not possible to do for a moment.

[siddas27]

@saikishor @Vayrex Did you find anything?

[saikishor]

@saikishor @Vayrex Did you find anything?

No not really.