Why i get 100% accuracy using CVPartion and SVM

7 次查看（过去 30 天）
nurin noor
nurin noor 2021-6-17
评论： nurin noor 2021-6-24
Hi everyone, i am new to machine learning. I am trying to classify "model1". I used cv partition with 70% of test and 30% of training. However, i am getting 100% accuracy. i am afraid i am using the same data to test and train but i thought cvpartition would help to seperate the data, right? Or i am using the same data for train and testing? Here is my code. I was referring the code from here
https://www.mathworks.com/matlabcentral/answers/377839-split-training-data-and-testing-data

请先登录，再回答此问题。

采纳的回答

Asvin Kumar
Asvin Kumar 2021-6-24
Your usage of cvpartition is correct. You are not using the same data for training and testing.
Your SVM jusr seems to be working very well.
  3 个评论
显示 1更早的评论
Asvin Kumar
Asvin Kumar 2021-6-24
Yes, that's what I meant. Everything should be working fine as your cvparition is correct. Data test and training are different.
Why the accuracy is 100% depends on the specific problem that you are trying to solve. SVMs just might be well suited for your data.
nurin noor
nurin noor 2021-6-24
i see. very much understood. it is such a relief to know my SVM implementation is correct. Thank you so much !!

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Classification 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by