Gazenet DeepStream Example

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Hi there,

I have gone through the provided notebooks to retrain the Gazenet model from the provided DeepStream Notebooks. But I am having trouble integrating the model into a DeepStream pipeline.

Does anyone have an example of how to use the GazeNet model (either Trained\Deployable), in a DeepStream pipeline? I have successfully generated a new etlt and also transformed it to a engine file, but I’m a bit stuck.

3

See https://docs.nvidia.com/tlt/tlt-user-guide/text/gaze_estimation/gaze_estimation.html#deploying-to-the-tlt-cv-inference-pipeline

The pretrained model for gaze estimation provided through NGC is available by default to use inside the TLT CV Inference Pipeline. You can also deploy a model trained through TLT workflow to the TLT CV Inference Pipeline. Refer to TLT CV Quick Start Scripts section for instructions of both options.

Please follow above inference pipeline.

5

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.