Run tao maskrcnn inference in Python without cmd line

• Hardware (RTX 3090 → Ubuntu 18.04)
• Network Type (maskrcnn)
• TLT Version: TAO Toolkit 3.0-21.11
• Tensorrt version: 8.0.1
• Issue: I want to include the inference process as a part of a small pipeline and do not want to run inference using "tao" command.

From my understanding, tao maskrcnn inference . internally calls a python inference script, is it possible to use the same script to run the tao model within a python-based pipeline?

Temporally you can run the inference with

python /usr/local/lib/python3.6/dist-packages/iva/mask_rcnn/scripts/inference.pyc xxx  

I will implement the inference in triton-app for mask_rcnn.

1 Like

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