Is TensorRT OSS necessary?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

In the TAO doc for deploy yolov4 model, it say TensorRT Open Source Software (OSS) is necessary. However in deepstream_tao_apps github repo, it say TensorRT OSS after deepstream 6.1.1 is not needed. So which statement is correct for deepstream 6.1.1?

https://docs.nvidia.com/tao/tao-toolkit/text/ds_tao/yolo_v4_ds.html#tensorrt-open-source-software-oss

• DeepStream Version 6.1.1

3

This is DeepStream TAO sample apps repo but not TensorRT github repo. https://github.com/NVIDIA-AI-IOT/deepstream_tao_apps/tree/master/TRT-OSS/Jetson#build-jetson-tensorrt-oss-plugin)

We just say that the sample apps do not need TensorRT OSS.

4

So I do not need to build TensorRT OSS Plugin if I want to use yolov4 model in Deepstream 6.1.1. Is that correct?

5

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. Thanks

This is the branch for DeepStream 6.1.1 : NVIDIA-AI-IOT/deepstream_tao_apps at release/tao3.0_ds6.1.1ga (github.com)

7

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