How can I split data train, validation using for classificaiton learner

4 次查看（过去 30 天）
beyoglu
beyoglu 2023-6-5
评论： Govind KM 2023-6-6
Hello, is there a way to select the train and validation data separately from the separate data in the workspace for classification learner? Classification Learner interface does it by splitting the train data into %train and %test as a deafult. I need this to take advantage of the classification learner.
Kind regards

请先登录，再回答此问题。

回答（1 个）

Govind KM
Govind KM 2023-6-5
You can set the percentage of data to be reserved for testing or even import a test data set through the Test section on the Classification Learner tab. You can refer to these documentation sites for more information :
https://in.mathworks.com/help/stats/select-data-and-validation-for-classification-problem.html (Section : Reserve Data for Testing)
https://in.mathworks.com/help/stats/assess-classifier-performance.html#mw_bce8ad28-f1d5-48fa-be79-9c272149a135 (Section: Evaluate Test Set Model Performance)
  2 个评论
beyoglu
beyoglu 2023-6-5
Let's assume that we have data from three separate datasets, train validation and test. We will evaluate their performance. In the link, the random part of the data as train and test is explained.
best regards
Govind KM
Govind KM 2023-6-6
While creating a new session, you can select holdout validation and select a percentage of data to be used as a validation set. This can help you if you want to set a specific number of samples for validation.
I don't think you can specify the validation data separately as of now.

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 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