# \--disable\_group\_convolution

**URL:** <https://community.ultralytics.com/t/disable-group-convolution/390>\
**Category:** Support\
**Tags:** support, yolo\
**Created:** [October 23, 2024, 8:52pm UTC](https://community.ultralytics.com/t/disable-group-convolution/390 "2024-10-23T20:52:23Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![ABest2](https://avatars.discourse-cdn.com/v4/letter/a/cdc98d/32.png) [@ABest2](https://community.ultralytics.com/u/ABest2)\
**Post date:** [October 23, 2024, 8:52pm UTC](https://community.ultralytics.com/t/disable-group-convolution/390/1 "2024-10-23T20:52:23Z")

</div>

I am trying to export a YOLOv10 model to tflite for use in the NPU of an NXP i.MX8M Plus device. I am unable to build the int8 quantized tflite file and I get the following warning:

WARNING: This model contains GroupConvolution and is automatically optimized for TFLite, but is not output because saved\_model does not support GroupConvolution. If saved\_model is needed, specify --disable\_group\_convolution to retransform the model.

Where do I use the --disable\_group\_convolution option it indicates is necessary? It appears to be related to an onnx2tf library but I don’t know how it relates to the model.export call from Ultralytics.

Thank you

---

<div class="post-metadata">

**Author:** ![pderrenger](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/pderrenger/32/73_2.png) [@pderrenger](https://community.ultralytics.com/u/pderrenger)\
**Post date:** [October 24, 2024, 12:35am UTC](https://community.ultralytics.com/t/disable-group-convolution/390/2 "2024-10-24T00:35:10Z")

</div>

Hello!

It looks like you’re encountering an issue with exporting your YOLOv10 model to TFLite due to the GroupConvolution operation. This is a common challenge when working with certain hardware accelerators like the NPU on the NXP i.MX8M Plus.

To address this, you can try the following steps:

1. **ONNX to TFLite Conversion** : The warning suggests using the `--disable_group_convolution` option during the ONNX to TFLite conversion process. This option is typically used with the `onnx2tf` tool. You might need to manually convert your ONNX model to TFLite using this tool and specify the option to disable group convolutions.

2. **Exporting with Ultralytics** : When using Ultralytics to export your model, ensure you’re following the correct export process. You can refer to the [Ultralytics TFLite Export Guide](https://docs.ultralytics.com/integrations/tflite/) for detailed instructions.

3. **Code Example** : If you haven’t already, you can start by exporting your model to ONNX using Ultralytics:

4. **Manual Conversion** : After exporting to ONNX, use the `onnx2tf` tool with the `--disable_group_convolution` option to convert to TFLite.

If you continue to face issues, please ensure you’re using the latest version of the Ultralytics package. Feel free to check out the [Ultralytics documentation](https://docs.ultralytics.com/) for more resources.

I hope this helps! Let us know if you have any more questions 😊.

---

<div class="post-metadata">

**Author:** ![Toxite](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/toxite/32/123_2.png) [@Toxite](https://community.ultralytics.com/u/Toxite)\
**Post date:** [October 24, 2024, 1:59pm UTC](https://community.ultralytics.com/t/disable-group-convolution/390/3 "2024-10-24T13:59:34Z")

</div>

`ultralytics` uses onnx2tf to convert from ONNX to TF format. `disable_group_convolution` is [enabled](https://github.com/ultralytics/ultralytics/blob/be40a45ec32d9173ff42b4bdb00dbfe5a8c7a838/ultralytics/engine/exporter.py#L906). Are you using the latest `ultralytics` ?

---

<div class="post-metadata">

**Author:** ![ABest2](https://avatars.discourse-cdn.com/v4/letter/a/cdc98d/32.png) [@ABest2](https://community.ultralytics.com/u/ABest2)\
**Post date:** [October 24, 2024, 7:54pm UTC](https://community.ultralytics.com/t/disable-group-convolution/390/4 "2024-10-24T19:54:32Z")

</div>

Hi @Toxite and @pderrenger,

Thank you for your quick replies. Using the latest version of Ultralytics does in fact fix my issue.

Thank you,  
Aaron