Using Weighted Classes in CNN
显示 更早的评论
In trying to set up my CNN layers with weighted classes I am getting an error that states:
"Error using classificationLayer>iParseInputArguments (line 58)
'ClassWeights' is not a recognized parameter. For a list of valid name-value pair arguments, see the
documentation for this function."
I am unsure if I'm using the class weights incorrectly. The following are the layers of my network:
classes = ["0","1"];
classWeights = 1./countcats(train_output);
classWeights = classWeights'/mean(classWeights);
layers = [
imageInputLayer([480 1 1])
convolution2dLayer([102 1],3,'Stride',1)
batchNormalizationLayer
leakyReluLayer
maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
convolution2dLayer([24 1],10,'Stride',1)
batchNormalizationLayer
leakyReluLayer
maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
convolution2dLayer([11 1],10,'Stride',1)
batchNormalizationLayer
leakyReluLayer
maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
convolution2dLayer([9 1],10,'Stride',1)
batchNormalizationLayer
leakyReluLayer
maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
fullyConnectedLayer(30)
fullyConnectedLayer(10)
fullyConnectedLayer(2)
softmaxLayer
classificationLayer('Classes',classes,'ClassWeights',classWeights)];
This error occurs with and without classes present in the brackets.
采纳的回答
Rishik Ramena
2021-3-21
0 个投票
The 'ClassWeights' property for the classificationLayer has been introduced in MATLAB R2021a. So if you are running a version prior to this, you are supposed to get this error. Please find the documentation for your installed MATLAB version here.
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 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 
