# Ultralytics platform

**URL:** <https://community.ultralytics.com/t/ultralytics-platform/1911>\
**Category:** Ultraltyics Platform\
**Created:** [April 4, 2026, 10:17am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911 "2026-04-04T10:17:32Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![Miguel\_Wisintainer](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/miguel_wisintainer/32/1460_2.png) [@Miguel\_Wisintainer](https://community.ultralytics.com/u/Miguel_Wisintainer)\
**Post date:** [April 4, 2026, 10:17am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911/1 "2026-04-04T10:17:32Z")

</div>

Hi,

I am using ultralytics platform to train my monkey database class, using the YOLO8N–CLS, all going well, i can test the ultralytics predict to certify the correct train and after converted to my SG2002 hardware, all inferences goes well, near to 100%

When i used the YOLO11N-CLS with my same monkey database, i see something weird in my hardware inference, all with values to much far to 99%, then i back to to ultralytics platform and see the same on predict ☹

not detects “BARBIE” monkey

and backing to the yolov8n-cls, all is good, its “BARBIE” monkey

Can you see that ?

Thanks

---

<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:** [April 4, 2026, 10:45am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911/2 "2026-04-04T10:45:24Z")

</div>

How large is your dataset? How many images do you have?

---

<div class="post-metadata">

**Author:** ![Miguel\_Wisintainer](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/miguel_wisintainer/32/1460_2.png) [@Miguel\_Wisintainer](https://community.ultralytics.com/u/Miguel_Wisintainer)\
**Post date:** [April 4, 2026, 10:50am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911/3 "2026-04-04T10:50:45Z")

</div>

2Gbytes  
2200 images, 44 classes

I am trainning now on COLAB to see if is a ultralytics platform bug.

PS: in some moment ultralytics platform reported “low memory” and aborted

---

<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:** [April 4, 2026, 11:19am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911/4 "2026-04-04T11:19:11Z")

</div>

Can you provide the link to your project on Ultralytics Platform?

---

<div class="post-metadata">

**Author:** ![Miguel\_Wisintainer](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/miguel_wisintainer/32/1460_2.png) [@Miguel\_Wisintainer](https://community.ultralytics.com/u/Miguel_Wisintainer)\
**Post date:** [April 4, 2026, 11:48am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911/5 "2026-04-04T11:48:58Z")

</div>

[Wizardly Swan Models by Miguel Wisintainer](https://platform.ultralytics.com/miguel-wisintainer/wizardly-swan)

---

<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:** [April 5, 2026, 1:01am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911/6 "2026-04-05T01:01:26Z")

</div>

Thanks for sharing the [Ultralytics Platform project link](https://platform.ultralytics.com/miguel-wisintainer/wizardly-swan) — that helps.

The earlier `low memory` abort is the biggest clue here. That usually points more to a training/resource issue than a `predict` bug, similar to the [Platform troubleshooting guidance](https://docs.ultralytics.com/platform/). With 2200 images across 44 classes, Ultralytics YOLO11-CLS can also be a bit more sensitive than your YOLOv8n-cls run.

If your Colab test with the latest `ultralytics` shows the same result, then it’s probably not Platform-specific. I’d mainly verify that you exported/used `best.pt` and not `last.pt`, then compare the YOLO11 run’s `top1` and confusion matrix against the YOLOv8 run. If the Platform run fails again, try the same setup with a smaller batch size.

---

<div class="post-metadata">

**Author:** ![Miguel\_Wisintainer](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/miguel_wisintainer/32/1460_2.png) [@Miguel\_Wisintainer](https://community.ultralytics.com/u/Miguel_Wisintainer)\
**Post date:** [April 5, 2026, 1:58am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911/7 "2026-04-05T01:58:27Z")

</div>

Thank you!!!
