Bounding boxes on images during yolo training goes all over the place

Support YOLO
1

I used roboflow to annotate my images, see example below:

sample image
sample image1033×1023 221 KB

then i download my annotated image dataset from roboflow.

when i train yolo using the the dataset, i check the training and validation images after training, and i saw that the bounding boxes go all over the place, see example below:

train_batch5101
train_batch51011920×1920 784 KB

i checked the bounding boxes on the dataset that i downloaded to see whether they are on correct places, and it seems they are… but when i run the training, the training shows me that the bounding boxes are not in the right place… and this makes the trained model detect wrongly

if someone knows why this bug is happening and how to solve it, i will be very grateful…

2

What format did you use for download?

1 Like
3

Looking at your example annotation image, there are annotations that are not boxes.

1000009921
10000099211080×1572 227 KB

These would not be supported for a detection model, as they have more than four corners.

1 Like
4

thanks for the reply… i used yolov11 format for my dataset (using roboflow)

5

thank you for your response…
what do you mean, if i used polygon, it is not supported in training yolo model?
does it mean, i have to use only rectangles (with 4 corners) or any shaped polygon as long as they have 4 corners (rhombus and the likes)?

6

You used both which is why the dataset is broken. You should either stick to polygons or boxes. You shouldn’t mix both type of annotation in the same dataset.