# Yolov11 OBBs discarded

**URL:** <https://community.ultralytics.com/t/yolov11-obbs-discarded/1647>\
**Category:** Discussion\
**Tags:** troubleshooting, question, code\
**Created:** [November 19, 2025, 1:26am UTC](https://community.ultralytics.com/t/yolov11-obbs-discarded/1647 "2025-11-19T01:26:37Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Martin\_Munoz](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/martin_munoz/32/1137_2.png) [@Martin\_Munoz](https://community.ultralytics.com/u/Martin_Munoz)\
**Post date:** [November 19, 2025, 1:26am UTC](https://community.ultralytics.com/t/yolov11-obbs-discarded/1647/1 "2025-11-19T01:26:37Z")

</div>

Hi everyone,

I’m training a model with **YOLO11-OBB** using **4-point polygon OBBs** (not cx/cy/w/h/angle), and I’m running into a consistent issue: **some objects are disappearing during training**. The polygons are being silently discarded, and I can’t figure out why.

### **What I’m observing**

- In `train_batch.jpg`, some objects that _definitely_ have a valid 4-point polygon in the label file appear **without any box**.

- Other polygons are shown correctly.

- No warnings or errors are printed — the polygon is just ignored.

- The dataset is 100% verified, and **I already validated the polygons manually and programmatically** before training:

### **My polygon format**

Each line is:

```auto
<class> x1 y1 x2 y2 x3 y3 x4 y4 (normalized)

```

This is the Ultralytics OBB polygon format for YOLO11.

### **Training configuration (relevant parts)**

- `augment=False`

- `mosaic=0`

- `mixup=0`

- `cutmix=0`

- `copy_paste=0`

- `nms=False` (default override)

- `overlap_mask=True`

- `amp=True`

- CPU training  
No geometric/crop augmentations should be affecting polygons.

### **What I already ruled out**

- ✔ Polygons fully outside the image → none

- ✔ Polygons clipped to zero area → none

- ✔ Polygons too small → none

- ✔ Wrong class count → correct

- ✔ Wrong normalization → correct

- ✔ Wrong point order → all clockwise

- ✔ Self-intersections → none detected

- ✔ Degenerate OBBs (collinear points) → none

So the polygons _should_ be valid.

### **My question**

**What are the internal reasons why YOLO11-OBB may discard a 4-point polygon during training, even if the annotation looks valid?**

Possible causes I’m trying to confirm:

- Does YOLO drop polygons whose minimum bounding rectangle becomes too small after resizing?

- Does Ultralytics clip polygons again internally and reject them if area \< threshold?

- Does OBB augmentation internally convert polygons to RBOX or MASK and fail?

- Could `overlap_mask=True` hide polygons in the visualization even if they exist?

- Is there a debugging flag to print WHY a polygon was removed?

- Is there any difference in handling polygons during caching?

### **What I need**

I’m looking for advice on how to:

1. **Enable verbose debugging for polygon filtering**

2. **Understand internal Ultralytics filters (min size, invalid clipping, etc.)**

3. **Check if the polygon is being dropped during preprocessing, augmentation, caching, or visualization**

4. **Confirm if the training has a hidden filter (like min\_size\_ratio) for OBBs**

If anyone has experience with polygons being discarded in YOLO11-OBB — especially 4-point OBB polygons — I’d appreciate any insights.

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:** [November 19, 2025, 5:02am UTC](https://community.ultralytics.com/t/yolov11-obbs-discarded/1647/2 "2025-11-19T05:02:13Z")

</div>

It can be discarded if it has some extreme aspect ratio

> <https://github.com/ultralytics/ultralytics/blob/5c226935aa6d7651d1861968f713dfba027a5089/ultralytics/data/augment.py#L1329>