why can imageInputLayer of 'deep network designer' app not be edited?

1 次查看(过去 30 天)
I want to edit the mean and std in imageInputLayer, but it is settled and can not be eidted, as follow:
so, how to edit it directly by using 'deep network designer'?

采纳的回答

Raynier Suresh
Raynier Suresh 2021-1-20
As of now the Mean and StandardDeviation cannot be modified directly in the Deep Network Designer. A work around for this is to define that layer in the MATLAB Terminal and then import it into the Deep Network Designer.
To define the layer with Mean and StandardDeviation you can use the below code.
inputlayer = imageInputLayer([28 28 3],'Name','input','Normalization','zscore','Mean',ones(1,1,3),'StandardDeviation',ones(1,1,3))
Refer the below link for more information on defining the image input layer:https://www.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.imageinputlayer.html

更多回答(0 个)

类别

Help CenterFile Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

产品


版本

R2020a

Community Treasure Hunt

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

Start Hunting!

Translated by