3

I downloaded the object model yolov7 (https://github.com/WongKinYiu/yolov7) and the coco dataset. Then there are the folders coco\images and coco\labels.
I opened the image "coco\images\train2017\000000000034.jpg" and the corresponding label file "coco\labels\train2017\000000000034.jpg".
An annotation for the yolo-model has to be in the form:
<object_class> <x_center> <y_center>

The content of the label file is:
22 0.00746875 0.0539294 0.117891 0.0921412 0.231297 0.110118 0.2895 0.0674118 0.331281 0.0472 0.3865 0.0696706 0.423813 0.0943765 0.446188 0.105624 0.467078 0.1528 0.517813 0.182024 0.577516 0.253929 0.658094 0.379765 0.690922 0.532588 0.687937 0.6 0.650625 0.555059 0.658094 0.644941 0.668547 0.755059 0.676 0.838212 0.658094 0.894376 0.613328 0.925835 0.589453 0.914612 0.590938 0.856188 0.552141 0.791012 0.523781 0.725835 0.528266 0.633718 0.498422 0.577529 0.444703 0.505624 0.407391 0.505624 0.395453 0.541576 0.417844 0.591012 0.450672 0.642706 0.456641 0.642706 0.461109 0.725835 0.458125 0.786518 0.450672 0.853929 0.444703 0.898871 0.401422 0.869671 0.411875 0.815741 0.423813 0.734824 0.425297 0.694376 0.361125 0.608988 0.316359 0.588753 0.280547 0.703365 0.271594 0.757294 0.261141 0.829224 0.268609 0.869671 0.277562 0.901129 0.250703 0.937082 0.222344 0.939318 0.231297 0.901129 0.222344 0.844941 0.238766 0.7236 0.246219 0.642706 0.271594 0.510118 0.182062 0.507859 0.0999844 0.525835 0.0208906 0.494376 0.0015 0.0516941

For what all numbers stand for?

Albi
  • 41
  • 3
  • The number looks like normalized values for the segmentation of the image. The first number corresponds to the class label, and the point makes a mask for the object detected. – Tanveer Jan Aug 09 '22 at 15:48
  • So, three numbers as a triple has the RGB information? What do you mean with segmentation of the image? – Albi Aug 10 '22 at 05:57
  • Segmentation draw a mask around the object. So the numbers above represent the coordinates for the mask. Similar to bounding box but bounding box have 4 values (x, y, width, height), a segmentation have a mask. The number of points in a mask are not always same in number so you will see different number of points for different object or even for same object. [Masks](https://images.app.goo.gl/5TFyYeLghwu6VQY39) in the image above you can see that there are bounding boxes with masks. so each value represent a point of the mask – Tanveer Jan Sep 21 '22 at 21:00
  • @TanveerJan do you know how data is normalaized? have this data width and height too? thanks – Tlaloc-ES Nov 14 '22 at 21:50

2 Answers2

0

I think you downloaded the segmentation dataset. Go in the cloned yolov7 directory and run

bash scripts/get_coco.sh

to get the object detection dataset

kurdoglu
  • 1
  • 1
0

The number looks like normalized values for the segmentation of the image. The first number corresponds to the class label, and the point makes a mask for the object detected

Segmentation draw a mask around the object. So the numbers above represent the coordinates for the mask. Similar to bounding box but bounding box have 4 values (x, y, width, height), a segmentation have a mask. The number of points in a mask are not always same in number so you will see different number of points for different object or even for same object. Masks in the image above you can see that there are bounding boxes with masks. so each value represent a point of the mask

Tanveer Jan
  • 61
  • 2
  • 2
  • 11