# Nms implemented in torch purly, supporting export onnx

**URL:** <https://community.ultralytics.com/t/nms-implemented-in-torch-purly-supporting-export-onnx/2123>\
**Category:** Community Showcase\
**Tags:** project, onnx\
**Created:** [July 17, 2026, 8:22am UTC](https://community.ultralytics.com/t/nms-implemented-in-torch-purly-supporting-export-onnx/2123 "2026-07-17T08:22:40Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![yxdragon](https://avatars.discourse-cdn.com/v4/letter/y/96bed5/32.png) [@yxdragon](https://community.ultralytics.com/u/yxdragon)\
**Post date:** [July 17, 2026, 8:22am UTC](https://community.ultralytics.com/t/nms-implemented-in-torch-purly-supporting-export-onnx/2123/1 "2026-07-17T08:22:40Z")

</div>

(Here)[[https://github.com/VectorElectron/yolov11\](https://github.com/VectorElectron/yolov11%5C)] is a sleek, professional, and exciting draft for your post, tailored for platforms like GitHub, LinkedIn, or developer forums (like WeChat Moments or Twitter/X).

## 🚀 Fully End-to-End YOLO: Merging Resize, Core Model, and NMS into a Single ONNX File!

Tired of dealing with messy preprocessing (resize/normalization) and heavy Python/C++ post-processing (NMS) outside of your model? I’ve wrapped the **entire pipeline** —from raw uint8 images to final bounding boxes—into **one single ONNX file**.

This approach delivers true **plug-and-play, end-to-end deployment** for web frontends, edge devices, or localized runtimes.

### 🌟 Key Features

- **Zero-Dependency Pipeline** : No more manual bounding box parsing or custom NMS C++ modules. The model accepts a raw `[H, W, 3]` uint8 image and outputs final, scaled coordinates directly.

- **Mathematical NMS** : Uses a batch-and-class isolated IoU graph lookup table (LUT) implemented directly in PyTorch operators—fully compatible with ONNX export.

- **Fully Dynamic Input** : Supports dynamic image resolutions, automatically scaling coordinates back to the original input size.

- **Seamless Merging** : Combines three independent stages (Preprocess, Core YOLO, and Post-NMS) into a unified computational graph using `onnx.compose`.

---

<div class="post-metadata">

**Author:** ![discourse\_ai\_spam](https://avatars.discourse-cdn.com/v4/letter/d/c68b51/32.png) [@discourse\_ai\_spam](https://community.ultralytics.com/u/discourse_ai_spam)\
**Post date:** [July 17, 2026, 8:22am UTC](https://community.ultralytics.com/t/nms-implemented-in-torch-purly-supporting-export-onnx/2123/2 "2026-07-17T08:22:44Z")

</div>



---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/flex001/uploads/ultralytics1/original/1X/88e5a5f6a5f787a9b0fda229002f75ccfdc31c39.png) [@system](https://community.ultralytics.com/u/system)\
**Post date:** [July 17, 2026, 3:48pm UTC](https://community.ultralytics.com/t/nms-implemented-in-torch-purly-supporting-export-onnx/2123/3 "2026-07-17T15:48:40Z")

</div>


