Clear Filters
Clear Filters

Error evaluation on convolutional net

1 view (last 30 days)
Simon
Simon on 22 Mar 2017
Commented: Jay on 18 May 2017
I have trained a conv net, using imds function as datastore and trainNetwork for the training. I would like to plot something similar to the matlab function "plotperform", but I cannot get that function working, since it requires another type of input, which the trainNetwork does not output. I need to know, how to plot the validation error together with the training error.

Answers (1)

Nanda Gupta
Nanda Gupta on 30 Mar 2017
I understand that you want to plot the validation error along with the training error for a ConvNet, to generate a graph similar to the one generated by "plotperform" function.
In the training options for "trainNetwork", you can set the "OutputFcn" to a custom function so that you can explicitly plot the accuracy at each iteration of the training process. Check out this documentation for more information: https://www.mathworks.com/help/nnet/ref/trainingoptions.html#bvnn789
  2 Comments
Johannes Kvam
Johannes Kvam on 28 Apr 2017
As far as I can tell this only passes the training info structure which you then can use to show the training accuracy. For validation testing you'd need to also pass the current network to calculate its performance on an independent validation set to get the validation performance. Then show the validation performance together with the training performance. Is there anyway of doing this?
Jay
Jay on 18 May 2017
so isnt there any straight forward way to plot Validation and Test errors every epoch?

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!