# Can I convert the output from YOLOv8 Object Detection guide by Roboflow into an ONNX format?

**URL:** <https://discuss.roboflow.com/t/can-i-convert-the-output-from-yolov8-object-detection-guide-by-roboflow-into-an-onnx-format/2585>\
**Category:** 🤝  Community Help\
**Tags:** formats, convert\
**Created:** [July 6, 2023, 11:32pm UTC](https://discuss.roboflow.com/t/can-i-convert-the-output-from-yolov8-object-detection-guide-by-roboflow-into-an-onnx-format/2585 "2023-07-06T23:32:11Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![JUSTIN\_DENIEL\_AQUINO](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/justin_deniel_aquino/32/2313_2.png) [@JUSTIN\_DENIEL\_AQUINO](https://discuss.roboflow.com/u/JUSTIN_DENIEL_AQUINO)\
**Post date:** [July 6, 2023, 11:32pm UTC](https://discuss.roboflow.com/t/can-i-convert-the-output-from-yolov8-object-detection-guide-by-roboflow-into-an-onnx-format/2585/1 "2023-07-06T23:32:11Z")

</div>

I’m new to machine learning and I followed the step-by-step guide of Roboflow on how to create a YOLOv8 object detection model using my own dataset. Is it possible to convert what I got here into ONNX format? I need this format to use for other software. Any help would be appreciated thank you.

> **[Google Colaboratory](https://colab.research.google.com/drive/1xbhGXElLe1UiwQ7Nb3h_s-KR11izSIBx?usp=sharing)**

---

<div class="post-metadata">

**Author:** ![leo](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/leo/32/2228_2.png) [@leo](https://discuss.roboflow.com/u/leo)\
**Post date:** [July 7, 2023, 3:59am UTC](https://discuss.roboflow.com/t/can-i-convert-the-output-from-yolov8-object-detection-guide-by-roboflow-into-an-onnx-format/2585/2 "2023-07-07T03:59:46Z")

</div>

Hi @JUSTIN_DENIEL_AQUINO

Our YOLOv8 notebook only supports model exports with `.pt` PyTorch files. What’s your use case for exporting to ONNX?

For converting to ONNX,[PyTorch has a resource](https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html) on it

Also, if you want to deploy your model, you can consider one of our [deployment options](https://docs.roboflow.com/deploy/supported-deployment-devices), including our [hosted API](https://docs.roboflow.com/deploy/hosted-api) or packages like [roboflow.js](https://docs.roboflow.com/deploy/web-browser)