How to find the input/output layers names of tlt/etlt model

Accelerated Computing Intelligent Video Analytics TAO Toolkit
7

For gesturenet inference, there are two ways by default.

  1. See https://docs.nvidia.com/metropolis/TLT/tlt-user-guide/text/gesture_recognition.html#running-inference-on-the-model . You can download the notebook for reference. Integrating TAO Models into DeepStream — TAO Toolkit 3.22.05 documentation

  2. See https://docs.nvidia.com/metropolis/TLT/tlt-user-guide/text/gesture_recognition.html#deploying-to-the-tlt-cv-inference-pipeline
    You can deploy a model trained through TLT workflow to the TLT CV Inference Pipeline.