How to use DALI to preprocess in triton Inference

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) T4
• DeepStream Version 6.1
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.2
• NVIDIA GPU Driver Version (valid for GPU only) 11.4
• Issue Type( questions, new requirements, bugs)

Could you help us with sample python application for detection model .

Hi @h9945394143
Sorry, this is not DeepStream related! Could you ask this in forum - Data Processing - NVIDIA Developer Forums ?


For this, please refer to GitHub - NVIDIA-AI-IOT/deepstream_python_apps: DeepStream SDK Python bindings and sample applications

can we use this deepstream_python_apps/config_preprocess.txt at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub

for the preprocess of triton ?

Hi @h9945394143
You can refer to deepstream-ssd-parser sample which uses nvinferserver (DeepStream Triton plugin), in which there is pre-processing for nvinferserver .

May I know why you want to use DALI for pre-process? What’s the source and what pre-process do you want to do?

we want to explore Preprocess and Postprocess of triton to improve processing time, We use Video as well as image for Inferencing .

Can u help us with pre-process and post process techniques ?