How do you do multi-class classification with a CNN network?

25 views (last 30 days)
Currently I have a CNN network with a the classification layer.
net = alexnet;
layersTransfer = net.Layers(1:end-3);
numClasses = 5;
layers = [
fullyConnectedLayer(numClasses,'Name', 'fc','WeightLearnRateFactor',1,'BiasLearnRateFactor',1)
softmaxLayer('Name', 'softmax')
classificationLayer('Name', 'classOutput')];
There are 5 different classes and each image can have multiple classes. However I can not find a way to train a network where each image has more than one possible class. How can I change my network so I can train it with data where there are multiple labels?

Accepted Answer

Mahesh Taparia
Mahesh Taparia on 19 Apr 2021
As per your problem, I am assuming you are having multiple categorical objects in a single image. So the problem is no longer an image classification, it is an object detection problem. You can refer to the documentation of object detection, here are some useful links:
Hope it will help!

Sign in to comment.

More Answers (0)


Find more on Recognition, Object Detection, and Semantic Segmentation in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!