Hello guys, i'm trying to do this exemple of YOLOv2 with my own data:
https://www.mathworks.com/help/vision/ug/train-an-object-detector-using-you-only-look-once.html
but i have a problem with the vehicleDataset:
I don't know what i missed? Can you please help me?

 采纳的回答

Sailesh Kalyanapu
Sailesh Kalyanapu 2021-6-14

0 个投票

Hi,
In the example, the vehicleDatasetGroundTruth.mat file contains a MATLAB table variable called vehicleDataset”, which has the filenames and the bounding boxes for the ground-truth.
(Assuming you have your groundtruth table stored in ‘Damagevehicle.mat’ in the correct format) : You can modify the command to data.variablename where variablename is the variable representing your loaded truth table.
If you dont have a groundtruth table for your dataset, first create one in the format(Or make a copy) similar to the one in vehicleDatasetGroundTruth.mat and then load it into Matlab.

1 个评论

Thank you so muuuuch! Damagevehicle.mat is a ImageLabelerSession. I guess that's the problem

请先登录,再进行评论。

更多回答(0 个)

类别

帮助中心File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by