Deepstream L4T Helm chart + EfficientNet Model?

[Thaddeus]

Hi,

I’m looking to leverage Deepstream L4T - Intelligent Video Analytics Demo | NVIDIA NGC but wish to modify it in two ways, and therefore have 2 questions:

• In the values.yaml for cameras, it only lists RTSP as examples - can we not use USB/CSI cameras?
• By default it uses the trafficcamnet model, which changes would be required to use one of the EfficientNet models?

Thanks,

[kesong]

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

---

[Thaddeus]

• Hardware Platform (Jetson / GPU) : Jetson Nano
• DeepStream Version : 0.1.1
• JetPack Version (valid for Jetson only) : 4.6.1
• TensorRT Version : 8.2.1
• NVIDIA GPU Driver Version (valid for GPU only) : L4T 32.7.1
• Issue Type : Question
• How to reproduce the issue ? N/A
• Requirement details: In OP

[kesong]

Here is DS samples. Hope it helps.

C/C++ Sample Apps Source Details — DeepStream 6.0.1 Release documentation (nvidia.com)

[Thaddeus]

Appreciate the samples but I’m wondering if the helm chart can be customised to load different models/sources etc.

[Amycao]

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

What do you mean “helm chart can be customised to load different models/sources etc”?