Different Values of Bounding Boxes for different classes.

1 次查看（过去 30 天）
Hamza Afzal
Hamza Afzal 2021-2-20
评论： Image Analyst 2021-2-22
I am working on matlab example of object detection using YOLO v3.
I am using multiple classes (vehicles: cars,bus,trucks,sedan etc).
While reading example https://www.mathworks.com/help/deeplearning/ug/object-detection-using-yolo-v3-deep-learning.html?s_tid=srchtitle
There was written that :(Bounding boxes can not containing zeros/NaNs/Infs/empty), also the values of the bounding boxes should be finite, positive, non-fractional, non-NaN and should be within the image boundary with a positive height and width. So, say i am working with 5 classes. In an image, if there are two classes present, then it will give error for the bounding boxes of 3 other classes.
Can bounding boxes be just [0] for a class not present in an image. or is it an error ?
Can some one explain this?

请先登录，再回答此问题。

采纳的回答

Image Analyst
Image Analyst 2021-2-20
I don't think so. If the bounding box was [0], it would not even have produced that bounding box in the first place.
  9 个评论
显示 7更早的评论
Image Analyst
Image Analyst 2021-2-22
I don't know exactly how you're generating the table and how you're passing the table to the training software, but evidently you can only pass in a bounding box that is not empty, so make sure that is the case.

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Object Detection 的更多信息

标签

产品


版本

R2020a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by