Q&A for the webinar “Create Intelligent Places Using NVIDIA Pre-trained vision Models and DeepStream SDK”

Thank you for attending last week’s webinar, “Create Intelligent Places Using NVIDIA Pre-trained vision Models and DeepStream SDK”, presented by Monika Jhuria. We hope you found it informative. We received a lot of great questions at the end and weren’t able to respond to all of them. We are consolidating all follow-up questions and responding to TLT and Pre-trained model related topics in the following post.

You can watch the recording and download the presentation slides from the original webinar link https://info.nvidia.com/iva-occupancy-webinar-reg-page.html?ondemandrgt=yes

  1. Is any demo application example available on GitHub for the Peoplenet model ?

PeopleNet model will work with the reference deepstream app that’s provided in the SDK. The config files to run PeopleNet are also provided in the SDK. Take a look at the documentation. The app in this webinar will be released on GitHub shortly.

  1. Could you go over how one can retrain a model with TLT? Or direct me to the right resources to do so?

Check out our developer tutorial: https://developer.nvidia.com/blog/training-custom-pretrained-models-using-tlt/

  1. Are there pretrained models for overhead views?

No, not in the current peoplenet model. We plan to add more data for overhead views in future releases.

  1. Where can I find documentation for custom model creation?

Please check this: https://developer.nvidia.com/blog/training-custom-pretrained-models-using-tlt/

For the response to the follow-up questions related to DeepStream SDK, please visit DeepStream forum.

If you have more questions, please feel free to post your questions in the forum and we will further assist you

1 Like