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

Question

Michael Bilenko 2021-4-17

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/804606-how-do-you-do-multi-class-classification-with-a-cnn-network

评论： Mahesh Taparia 2021-4-24

Currently I have a CNN network with a the classification layer.

net = alexnet;
layersTransfer = net.Layers(1:end-3);
numClasses = 5;
layers = [
    layersTransfer
    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?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Mahesh Taparia 2021-4-19

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/804606-how-do-you-do-multi-class-classification-with-a-cnn-network#answer_678912

Hi

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!