Same training results for each epoch using LSTM sequence to sequence

2 次查看（过去 30 天）

显示更早的评论

Ismaeel 2022-12-29

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1886032-same-training-results-for-each-epoch-using-lstm-sequence-to-sequence

编辑： Ismaeel 2022-12-29

在 MATLAB Online 中打开

Dear all,

I am following the example given in:

https://www.mathworks.com/help/deeplearning/ug/sequence-to-sequence-regression-using-deep-learning.html

using different data but similar in structure to the one in the example.

The problem is when I train the data, the results for each epoch look the same (please see the picture attached).

I use the following setting options for training:

maxEpochs = 20;
miniBatchSize = 20;
options = trainingOptions('adam', ...
    'MaxEpochs',maxEpochs, ...
    'MiniBatchSize',miniBatchSize, ...
    'InitialLearnRate',0.01, ...
    'GradientThreshold',1, ...
    'Shuffle','never', ...
    'Plots','training-progress',...
    'Verbose',0);