Layers argument must be an array of layers or a layer graph.

3 次查看（过去 30 天）
PRAMOD A
PRAMOD A 2024-2-7
回答： Krishna 2024-2-10
XTrain = xlsread('R1_all_data.xlsx',1,'A1:G3788')';
YTrain = xlsread('R1_all_data.xlsx',1, 'H1:H3788')';
XTest = xlsread('R2_all_data.xlsx',1, 'A1:G3788')';
YTest = xlsread('R2_all_data.xlsx',1, 'H1:H3788')';
inputSize = 3788;
numResponses = 1;
numHiddenUnits = 5000;
layers = { sequenceInputLayer(inputSize)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numResponses)
regressionLayer };
opts = trainingOptions('adam', 'MaxEpochs', 1000, 'GradientThreshold', 0.01, 'InitialLearnRate',0.0001);
net = trainNetwork(XTrain,YTrain,layers,opts);
YPred1=predict(net,XTest)
  1 个评论
Matt J
Matt J 2024-2-7
编辑：Matt J 2024-2-7
You have posted only code. Do you have a question about it? If you are getting error messages please copy/paste them.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Krishna
Krishna 2024-2-10
Hello PRAMOD,
It appears that the issue you're encountering stems from an improper initialization of the layers object. The mistake was made by using curly braces {} to initialize:
layers = { sequenceInputLayer(inputSize)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numResponses)
regressionLayer }
Instead, you should initialize using square brackets [] like this:
layers = [ sequenceInputLayer(inputSize)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numResponses)
regressionLayer ]
I hope this correction resolves your problem.

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2022b

Community Treasure Hunt

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

Start Hunting!

Translated by