Classify Function predicting Nan Values instead of classes

12 次查看（过去 30 天）

显示更早的评论

Arpan Parikh 2020-2-19

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/506381-classify-function-predicting-nan-values-instead-of-classes

回答： Srivardhan Gadila 2020-2-21

I'm working on training an LSTM model.

Each input has 25 channels and sequenceLength of 313. There are 200 training samples.

Running the code outputs:

Final Predicted Value(predlabel), Training Data(lstm_arr), Training Label(classlabel):

All the predicted values are undefined values for some reason. Any reason why this is happening? What am I doing wrong?

btw I am running MATLAB on windows 10

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Srivardhan Gadila 2020-2-21

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/506381-classify-function-predicting-nan-values-instead-of-classes#answer_416680

Please refer to the following Why does LSTM sequence to label give undefined categories?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

类别

AI and Statistics Deep Learning Toolbox Train Deep Neural Networks Function Approximation, Clustering, and Control Function Approximation and Clustering

在 Help Center 和 File Exchange 中查找有关 Function Approximation and Clustering 的更多信息

标签

Community Treasure Hunt

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

Translated by