# Can i train model with Rectangle ratio images?

**URL:** <https://community.ultralytics.com/t/can-i-train-model-with-rectangle-ratio-images/1874>\
**Category:** YOLO\
**Tags:** support\
**Created:** [March 18, 2026, 1:20pm UTC](https://community.ultralytics.com/t/can-i-train-model-with-rectangle-ratio-images/1874 "2026-03-18T13:20:54Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![iscream](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/iscream/32/1296_2.png) [@iscream](https://community.ultralytics.com/u/iscream)\
**Post date:** [March 18, 2026, 1:20pm UTC](https://community.ultralytics.com/t/can-i-train-model-with-rectangle-ratio-images/1874/1 "2026-03-18T13:20:54Z")

</div>

Hi im trying to find USB camera and Thrmal camera module for my Xavier NX developer Kit.

I realized that those modules usually support 4:3 ratio images.

I’m worring about resizing image which could makes my model dumb.I cant find training options about images ratio.

And also im trying to modify v8’s input 1\*3640640 into 1\*4\*640\*\*640 for my thermal camera data

or making additional backbone which is only for thermal data (in this case I will use C2PSA to

integrate two other tensor - one is from RGB backbone and the other is from Thermal backbone-)

Is this dual-backbone idea possible in ultralytics? or should i give up ur pre-trained weight files and make my own torch model?

---

<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:** [March 18, 2026, 1:24pm UTC](https://community.ultralytics.com/t/can-i-train-model-with-rectangle-ratio-images/1874/2 "2026-03-18T13:24:28Z")

</div>

Image size aspect ratio doesn’t matter as long as you’re consistent between training and inference. Ultralytics performs the resizing. You don’t need to resize.

For multi-channel, Ultralytics has support for it through TIFF files:

> **[Dataset YAML - COCO8-Multispectral Dataset](https://docs.ultralytics.com/datasets/detect/coco8-multispectral/#dataset-yaml)**
>
> The Ultralytics COCO8-Multispectral dataset is an advanced variant of the original COCO8 dataset, designed to facilitate experimentation with multispectral object detection models. It consists of the same 8 images from the COCO train 2017 set—4 for...

---

<div class="post-metadata">

**Author:** ![iscream](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/iscream/32/1296_2.png) [@iscream](https://community.ultralytics.com/u/iscream)\
**Post date:** [March 18, 2026, 1:33pm UTC](https://community.ultralytics.com/t/can-i-train-model-with-rectangle-ratio-images/1874/3 "2026-03-18T13:33:42Z")

</div>

Thanks for replying

what if thermal and RGB has different resolution??

As an example, RGB is 960 \* 720 _and IR is 256 \*_ 192  
both is 4:3 ratio  
Does ultralytics automatically resize this too?

---

<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:** [March 18, 2026, 5:01pm UTC](https://community.ultralytics.com/t/can-i-train-model-with-rectangle-ratio-images/1874/4 "2026-03-18T17:01:03Z")

</div>

No. They should be same resolution with the thermal image as 4th channel. You basically need to combine them to 4 channel images