Iris segmentation using UNET

I need to perform efficient iris segmentation from an eye. I would like to know the expected accuracy and speed of this task on a Jetson device. Additionally, I would appreciate guidance on which model to use and whether it is available in the TAO (Train, Adapt, Optimize) toolkit.

For segmentation network, you can use Mask_rcnn or Unet network.
They are available in TAO.

Thanks for the replay,
Can you please give me an idea about accuracy and speed in the case of UNET and MaskRCNN ?
SOM: Jetson Xavier


You can find the purpose-built models based on these two network in


Can we do any boundary level segmentation with any of the networks like MaskRCNN and UNET or TAO have any other method for that ?

In TAO, there are Mask_rcnn, Unet and SegFormer.

Thanks Morganh

Is there any tool for creating annotation in segmentaion from nvidia side.

There is not label tool from TAO.
You can refer to Sloth and Label-Studio tools.


This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.