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?

 Réponse acceptée

Sailesh Kalyanapu
Sailesh Kalyanapu le 14 Juin 2021

0 votes

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 commentaire

Hind Haboubi
Hind Haboubi le 14 Juin 2021
Thank you so muuuuch! Damagevehicle.mat is a ImageLabelerSession. I guess that's the problem

Connectez-vous pour commenter.

Plus de réponses (0)

Catégories

En savoir plus sur Deep Learning Toolbox dans Centre d'aide et File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by