# YoloV3 without Batched NMS post processing code

**URL:** <https://forums.developer.nvidia.com/t/yolov3-without-batched-nms-post-processing-code/308073>\
**Category:** TAO Toolkit\
**Created:** [September 27, 2024, 8:53am UTC](https://forums.developer.nvidia.com/t/yolov3-without-batched-nms-post-processing-code/308073 "2024-09-27T08:53:47Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![abhimanyu.kspillai](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@abhimanyu.kspillai](https://forums.developer.nvidia.com/u/abhimanyu.kspillai)\
**Post date:** [September 27, 2024, 8:53am UTC](https://forums.developer.nvidia.com/t/yolov3-without-batched-nms-post-processing-code/308073/1 "2024-09-27T08:53:47Z")

</div>

I am using TAO Toolkit version 5.3.0 and has trained a YoloV3 model, which on conversion adds the BatchedNMS layer to it, which was not supported on my embedded device.

So I removed the Batched NMS layer as mentioned in this discussion.

> [@Errors while reading ONNX file produced by TAO 5](https://forums.developer.nvidia.com/t/errors-while-reading-onnx-file-produced-by-tao-5/264792/10):
>
> Please use below way to trim the onnx. For example, to trim [https://forums.developer.nvidia.com/uploads/short-url/tc4tmv15H16NiFPOqOa1QNswBnM.onnx](https://forums.developer.nvidia.com/uploads/short-url/tc4tmv15H16NiFPOqOa1QNswBnM.onnx) import onnx\_graphsurgeon as gs import numpy as np import onnx model = onnx.load("cardbox\_detection\_with\_yolov4\_tiny.onnx") graph = gs.import\_onnx(model) tensors = graph.tensors() graph.inputs = [tensors["Input"].to\_variable(dtype=np.float32, shape=( "N", 3,512,768))] graph.outputs = [tensors["box"].to\_variable(dtype=np.float32), tensors["cls"].to…

Requesting you help me with the post processing/inference code for the same withou BatchedNMS in it.

Thanks & Regards,  
Abhimanyu K S

---

<div class="post-metadata">

**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\
**Post date:** [September 27, 2024, 9:20am UTC](https://forums.developer.nvidia.com/t/yolov3-without-batched-nms-post-processing-code/308073/2 "2024-09-27T09:20:40Z")

</div>

> [@abhimanyu.kspillai](#):
>
> post processing/inference code for the same withou BatchedNMS in it

The official code of the BatchedNMS plugin is in [TensorRT/plugin/batchedNMSPlugin at 23.08 · NVIDIA/TensorRT · GitHub](https://github.com/NVIDIA/TensorRT/tree/23.08/plugin/batchedNMSPlugin).  
If the plugin exists, the boxes and scores are the two inputs of the `batchedNMSPlugin`.  
If you already remove the plugin, you can do the post-processing against the boxes and scores directly.

---

<div class="post-metadata">

**Author:** ![yingliu](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yingliu/32/136703_2.png) [@yingliu](https://forums.developer.nvidia.com/u/yingliu)\
**Post date:** [October 21, 2024, 8:57am UTC](https://forums.developer.nvidia.com/t/yolov3-without-batched-nms-post-processing-code/308073/3 "2024-10-21T08:57:05Z")

</div>

**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**

---

<div class="post-metadata">

**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\
**Post date:** [November 4, 2024, 8:57am UTC](https://forums.developer.nvidia.com/t/yolov3-without-batched-nms-post-processing-code/308073/4 "2024-11-04T08:57:52Z")

</div>

Closed on November 4, 2024, 8:57am UTC

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