# Using a self-trained model is unable to perform intelligent annotation

**URL:** https://community.ultralytics.com/t/using-a-self-trained-model-is-unable-to-perform-intelligent-annotation/2204
**Category:** Support
**Tags:** question
**Created:** [September 3, 2026, 9:41am UTC](https://community.ultralytics.com/t/using-a-self-trained-model-is-unable-to-perform-intelligent-annotation/2204 "2026-09-03T09:41:08Z")
**Posts on this page:** 3
**Page:** 1

<div class="post-metadata">

### Author: ![jinwei\_li](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/jinwei_li/32/1687_2.png) [@jinwei\_li](https://community.ultralytics.com/u/jinwei_li)
#### Post date: [September 3, 2026, 9:41am UTC](https://community.ultralytics.com/t/using-a-self-trained-model-is-unable-to-perform-intelligent-annotation/2204/1 "2026-09-03T09:41:08Z")

</div>

I created a dataset of 200 images through the ultralytics platform, which contained 6 categories. Then I trained a model named best.pt. Subsequently, I wanted to use the best.pt model for smart annotation, so I added another 1000 images to the original dataset. I carried out the annotation task in this way last week, but now I’m receiving the message: “This model’s classes do not match the dataset.” I can confirm that my categories have not been modified in any way. And everything was carried out normally last week. I hope to receive a response. Thank you.

---

<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: [September 3, 2026, 1:18pm UTC](https://community.ultralytics.com/t/using-a-self-trained-model-is-unable-to-perform-intelligent-annotation/2204/2 "2026-09-03T13:18:01Z")

</div>

Thanks for reporting.

We are looking into it.

---

<div class="post-metadata">

### Author: ![glenn-jocher](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/glenn-jocher/32/83_2.png) [@glenn-jocher](https://community.ultralytics.com/u/glenn-jocher)
#### Post date: [September 4, 2026, 9:16am UTC](https://community.ultralytics.com/t/using-a-self-trained-model-is-unable-to-perform-intelligent-annotation/2204/3 "2026-09-04T09:16:08Z")

</div>

@jinwei_li should be fixed now, can you please try again and let us know if this is solved for you?

I validate the fix I trained a model on an existing dataset, then went back to the dataset and deleted a few annotations and use auto annotation with the model I’d just trained and it’s working correctly for me.

 ![Screenshot 2026-09-04 at 11.12.28](https://us1.discourse-cdn.com/flex001/uploads/ultralytics1/original/2X/3/3f74e324163f84d2bff9d20ff941442c16faf4d5.webp)
