MATLAB Answers

object classes classification layer must be equal in the input trainingData plus 1 for the "Background" class

4 views (last 30 days)
Matpar on 18 Feb 2020
Commented: Matpar on 21 Feb 2020
Hi All Matlab folk,
I am trying to manually code the classes for my network can someone assist me please?
I am trying to gain a better understanding of this error! Can some one help me understand this error in an easier way please?
I changed the input layer details in the DAG network and still this it is arguing!
My Input layer:
imageInputLayer([32 32 3],"Mean",[],"Normalization","zerocenter", "Name","imageinput")
The number object classes in the network classification layer must be equal to the number of classes defined in the input
trainingData plus 1 for the "Background" class

Answers (1)

Raunak Gupta
Raunak Gupta on 21 Feb 2020
As per the example mentioned in trainRCNNObjectDetector the number of classes to be mentioned for training must be (objectClasses + 1) .The objectClasses should also be mentioned in a cell array which can represent the name of those classes. The fullyConnectedLayer will be having outputSize as (objectClasses + 1).You may look into the above-mentioned example for clarity about implementing the same.
  1 Comment
Matpar on 21 Feb 2020
that was not the issue I solve that aspect of it the bounding box is not drawing and that is challenging me at the moment!
any suggesstions on bonding boxes, systax or a workable format?
let me know pal please!

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!

Translated by