accuracy of the svm model for multiple classes

6 views (last 30 days)
how i can calculate accuraccy of svm model for multiple class,for one vs all classifier, i calculate the maximum score of the tested data,

Answers (1)

Hari
Hari on 5 Sep 2023
Hi Rishika,
As per my understanding, you want to calculate the accuracy of an SVM model for multiple classes whose labels are predicted based on one-vs-all (also known as one-vs-rest) approach.
If you have trained the SVM model based on one-vs-all approach and have the test data and corresponding true labels. Then make predictions for the test data using your approach. By comparing the predicted labels (predictions) with the true labels, you can calculate the accuracy by dividing the number of correctly predicted data points by the total number of data points.
Refer to the below documentation to learn more about “Support Vector Machine Classification” using MATLAB.

Categories

Find more on Statistics and Machine Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!