Peoplenet inference tao deploy notebook

Please provide the following information when requesting support.

• Network Type (Detectnet_v2/peoplenet)

I want to run the notebook tao_deploy.ipynb [Google Colab]
to simply run peoplenet and see the output
on a sample video ,
I follow the steps and face this error at the end

/bin/bash: line 1: detectnet_v2: command not found
how could I fix it ?
can I run this notebook on my own ubuntu ?

Which cell did you run into above error? Then can you upload the full log when run this cell? Thanks.

after running step 7

## 7. Generate TRT engine file for the ptm’s etlt file

the error occurred.

About the error log , just this single line appeared on screen

/bin/bash: line 1: detectnet_v2: command not found

But there is a matter I am suspicious to, the tensorrt version is related to cuda 11.8, while the default cuda version of my colab is 12 . should I install cuda 11.8 on my colab as well ?

Please check above cells, especially cell 5. To check if there is any error.

This is fixed
I can run it on an image
Now If I want to run the model on camera, with an rtsp link. could you please give me a hint in this problem too ?

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.

Could you share the experience what happens and what did you change? Thanks a lot.

As discussed in another topic you created, you can run deepstream_tao_apps. There is setting “4=RTSPStreaming” for the input file.

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

Note: Currently, the colab notebooks can work now on ubuntu22.04.
Please run notebooks in Running TAO Toolkit on Google Colab - NVIDIA Docs

More info can be found in GitHub - NVIDIA-AI-IOT/nvidia-tao.