How can I get a value of Training RMSE of the LSTM training?
13 ビュー (過去 30 日間)
古いコメントを表示
Nazila Pourhajy
2021 年 10 月 16 日
コメント済み: Nazila Pourhajy
2021 年 11 月 23 日
Hi everyone.
I trained LSTM network for price prediction.I have info.TrainingRMSE of LSTM. But I want to get final value of RMSE for training to compare between training RMSE and testing RMSE.
How can I calculate final value of training RMSE? Please help me.Thanks.
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/769011/image.jpeg)
And I have another question. Why some values of ValidationRMSE is NaN?
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/769016/image.jpeg)
0 件のコメント
採用された回答
Niccolò Dal Santo
2021 年 11 月 11 日
Hi Nazila,
You can access the final Training and Validation RMSE from the info struct returned by trainNetwork, by accessing the last element:
>> info.TrainingRMSE(end)
Some values of the vector info.ValidationRMSE are NaN since they correspond to the iterations where the model is not evaluated on the validation dataset. You can set how often the model is evaluated on the validation dataset with the ValidationFrequency training option.
その他の回答 (0 件)
参考
カテゴリ
Help Center および File Exchange で Get Started with Statistics and Machine Learning Toolbox についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!