How to train an Annotation Model

I posted a thread asking about both Clara Deploy and Train but realized I should probably post separate in their respective categories, sorry for the duplicate.

I cannot seem to find how to train an Annotation model? I see how to train classification and segmentation models, but annotation seems to be missing. As there are few annotation models in the NVIDIA archives for Clara 2.0 I assume you have to create many from scratch, and I see how you can do that with segmentation, but not how to create an annotation model from a segmentation model. I’ve seen the “AddExtremePointsChannel” function for simulating the extreme points inputs, but I don’t really know where to go from there. I saw this thread but it was a bit vague in how you actually go about training Annotation models.

Thank you!


Thanks for you interest in Clara Train. Similar to segmentation models; we do have MMARs available for annotation models on NGC. Training those models is conceptually similar. Perhaps you can take a look at the spleen example here where we have the training scripts and configs:

I was only looking at the documentation pages, didn’t realize the training scripts were in the downloaded models, my mistake. Thank you, that answered my question!