# TensorRT onnx parser + BatchedNMSDynamicPlugin

**URL:** <https://forums.developer.nvidia.com/t/tensorrt-onnx-parser-batchednmsdynamicplugin/189315>\
**Category:** TensorRT\
**Created:** [September 15, 2021, 1:15pm UTC](https://forums.developer.nvidia.com/t/tensorrt-onnx-parser-batchednmsdynamicplugin/189315 "2021-09-15T13:15:33Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![alphikuuuu](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@alphikuuuu](https://forums.developer.nvidia.com/u/alphikuuuu)\
**Post date:** [September 15, 2021, 1:15pm UTC](https://forums.developer.nvidia.com/t/tensorrt-onnx-parser-batchednmsdynamicplugin/189315/1 "2021-09-15T13:15:33Z")

</div>

Hello, we are using the Yolov5 model, we store it in ONNX. In our project, we use the TensorRT ONNX parser to parse it. Post-processing is now done on OpenCV on CPU.  
We want to change the post-processing to BatchedNMSPlugin so that it connects to the output of the ONNX parser.  
How can you do this?

## Environment

**TensorRT Version** :7.2.3.4  
**GPU Type** : RTX3060  
**Nvidia Driver Version** :  
**CUDA Version** : 11.1  
**CUDNN Version** :  
**Operating System + Version** : linux ubuntu 20.04  
**Python Version (if applicable)**:  
**TensorFlow Version (if applicable)**:  
**PyTorch Version (if applicable)**:  
**Baremetal or Container (if container which image + tag)**:

## Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

## Steps To Reproduce

Please include:

- Exact steps/commands to build your repro
- Exact steps/commands to run your repro
- Full traceback of errors encountered

---

<div class="post-metadata">

**Author:** ![spolisetty](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/spolisetty/32/14047_2.png) [@spolisetty](https://forums.developer.nvidia.com/u/spolisetty)\
**Post date:** [September 16, 2021, 4:37am UTC](https://forums.developer.nvidia.com/t/tensorrt-onnx-parser-batchednmsdynamicplugin/189315/2 "2021-09-16T04:37:28Z")

</div>

Hi,

Hope following will be helpful to you.

> **[Architecture Overview — NVIDIA TensorRT](https://docs.nvidia.com/deeplearning/tensorrt/latest/architecture/architecture-overview.html)**

> **[TensorRT/plugin/batchedNMSPlugin at master · NVIDIA/TensorRT](https://github.com/NVIDIA/TensorRT/tree/master/plugin/batchedNMSPlugin)**
>
> NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT. - NVIDIA/TensorRT

Thank you.