How do you do multi-class classification with a CNN network?
显示 更早的评论
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?
采纳的回答
Mahesh Taparia
2021-4-19
1 个投票
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!
4 个评论
Michael Bilenko
2021-4-22
Mahesh Taparia
2021-4-22
Usually an image is assigned as 1 label in case of image classification. So we use softmax classifier at the last layer. One possible approach for your problem is to replace that softmax layer with sigmoid layer with 5 inputs and 5 outputs (as numClasses = 5). It will give the probability of each class in that image. Use the custom loss layer at the end of the network (with classification loss of 5 classes) while doing training. This is a possible approach of multi label classification.
Michael Bilenko
2021-4-24
Mahesh Taparia
2021-4-24
You can refer the below links, it will be useful:
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Object Detection 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
