Is there a public implementation of Mask R-CNN in PyTorch and for the other state of the art models in Instance segmentation?
I search on github and didn’t find one.
Let me know if one exists.
If you’re looking to experiment with a bunch of different types of segmentation models you can take a look at this repo: https://github.com/achaiah/torchsample/tree/frankenstein I cloned @ncullen93’s excellent torchsample project and extended it into a bit of a monster 
with a bunch of open-source segmentation and classification models provided.
Cool. Did you look into training any instance aware segmentation architectures?
Presently, I want an instance aware segmentation architecture as a starting point for my work
Ah, no sorry I have not yet utilized any instance aware models.