Whether the nvinfer can work in parallel or not?

[wangyan11]

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) NX
**• DeepStream Version 5.1
**• JetPack Version (valid for Jetson only) 4.4
**• TensorRT Version 7.1
**• NVIDIA GPU Driver Version (valid for GPU only) 10.2
**• Issue Type( questions, new requirements, bugs) questions
**• How to reproduce the issue ?
This is development questions, we want to know whether the nvinfer can work in parallel or not
**• Requirement details
we want to build a pipeline like this, nvinfer in parallel, is it a possible plan?

[AastaLLL]

Hi,

Sorry for the late reply.

Yes, it is possible.
For example, in our pipeline below, We support multiple secondary nvinfer (classifier) at the same time:

https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Overview.html#deepstream-graph-architecture

Thanks.