How to feed annotated bounding boxes with atributes to rcnn?

Hi

So I've made myself a dataseset of annotated pictures. All rois have several atributes. I don't know how to feed them to fasterrcnnObjectDetector. Pliz help

Regards

'C:\Users\pawel\Documents\MATLAB\Datasetfinal\20200102_152050-1416x1062.jpg'	1x0 struct	1x1 struct	1x0 struct
'C:\Users\pawel\Documents\MATLAB\Datasetfinal\20200210_113007.jpg'	1x0 struct	1x0 struct	1x1 struct
'C:\Users\pawel\Documents\MATLAB\Datasetfinal\20200210_101150.jpg'	1x0 struct	1x0 struct	1x2 struct
'C:\Users\pawel\Documents\MATLAB\Datasetfinal\DSC02252.JPG'	1x0 struct	1x0 struct	1x1 struct
'C:\Users\pawel\Documents\MATLAB\Datasetfinal\DSC02218.JPG'	1x0 struct	1x0 struct	1x1 struct
'C:\Users\pawel\Documents\MATLAB\Datasetfinal\20200210_102559.jpg'	1x0 struct	1x0 struct	1x1 struct

Answer 1

[Madhav Thakker]

Hi Pawel,

Have a look at https://in.mathworks.com/help/vision/ug/object-detection-using-faster-r-cnn-deep-learning.html example which talks about how to train faster-RCNN on vehicle dataset in MATLAB.

Hope this helps.