# Converting yolov3 and yolov4 model to onnx without batchedNMS

**URL:** <https://forums.developer.nvidia.com/t/converting-yolov3-and-yolov4-model-to-onnx-without-batchednms/294228>\
**Category:** TAO Toolkit\
**Created:** [May 27, 2024, 12:39pm UTC](https://forums.developer.nvidia.com/t/converting-yolov3-and-yolov4-model-to-onnx-without-batchednms/294228 "2024-05-27T12:39:09Z")\
**Posts on this page:** 1\
**Showing post:** 3

<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:** [May 28, 2024, 2:42am UTC](https://forums.developer.nvidia.com/t/converting-yolov3-and-yolov4-model-to-onnx-without-batchednms/294228/3 "2024-05-28T02:42:30Z")

</div>

> [@venkatesha2411](#):
>
> Can we change the yolo\_export code in the backend without NMS branch while converting yolov3/v4 model to onnx

Yes, you can also change the export code.

> [@venkatesha2411](#):
>
> how do we do it on colab?

It is not very convenient in colab. But you can still refer to [Unable to export hdf5 to etlt after Tao Training on Colab - #9 by Morganh](https://forums.developer.nvidia.com/t/unable-to-export-hdf5-to-etlt-after-tao-training-on-colab/286328/9) and [Unable to export hdf5 to etlt after Tao Training on Colab - #11 by Morganh](https://forums.developer.nvidia.com/t/unable-to-export-hdf5-to-etlt-after-tao-training-on-colab/286328/11) about how to login docker and modify code.

---

_[View the full topic](https://forums.developer.nvidia.com/t/converting-yolov3-and-yolov4-model-to-onnx-without-batchednms/294228)._