How to plot confusion matrix?

Hello, i want to plot a confusion matrix, but i don't know witch are the true labels target and witch are predicted labels outputs.

plotconfusion(targets,outputs) plots a confusion matrix for the true labels targets and predicted labels outputs. Specify the labels as categorical vectors, or in one-of-N (one-hot) form.

Please help.

Answer 1

[Purvaja]

Hi @Niculai Traian,

According to your question, you want to know which variables would be the right arguments for “plotconfusion” function.

As mentioned in documentation:

“plotconfusion(targets,outputs) plots a confusion matrix for the true labels targets and predicted labels outputs.”

After observing your workspace variables, I have observed that you have “YTest” and “YPred” variables, which would signify “targets” and “outputs” arguments for “plotconfusion” function.

So you can implement your function as follows:

plotconfusion(YTest, YPred); 

For more clarification, the following documentation links would be helpful:

https://in.mathworks.com/help/deeplearning/ref/plotconfusion.html

You can also try “confusionmat” function :

https://in.mathworks.com/help/stats/confusionmat.html

You can try this command in your MATLAB command window for specific release documentation:

web(fullfile(docroot, 'images/ref/plotconfusion.html'))

For examples enter following command in your command window:

openExample('nnet/PlotConfusionMatrixUsingCategoricalLabelsExample') 

Hope this helps you!