MATLAB Answers

Is there any "regression" output layer equivalent to pixelClass​ificationL​ayer?

12 views (last 30 days)
Virginia Fernandez Gonzalez
Commented: Sai Bhargav Avula on 10 Aug 2020 at 4:41
I am working on a denoising Neural Network that has an image as input and outputs a denoised version of the image as output. I have created the network in Matlab, using the Deep Learning Toolbox, and now I need to train it. However, trainNetwork does not accept a Ground Truth that is not a categorical. I've doubled check my network and the issue might be that my last layer is a Classification Layer (pixelClassificationLayer). However, in my case, the problem is a regression one, where the value of each output pixel can correspond to any level of gray. I wondered, is there any regression equivalent to pixelClassificationLayer, or plausible alternative for Regression issues in Deep Learning Imaging?
Thank you very much.

  1 Comment

Binu on 29 Oct 2019
There is a regression layer where you basically swap the last layer from classification to regression. Also there are transfer learning methods to convert from a classification to regression . However I have not tried this on a pixelLevel problems.
Have you considered using your gray "levels" as a classes or bins and treat them as a classification problem?

Sign in to comment.

Answers (1)

Sai Bhargav Avula
Sai Bhargav Avula on 29 Oct 2019
Hi, I would recommend you trying the MATLAB way to network. Where you can convert to your layers to a dlnetwork
You can the following link for a detailed understanding of how to define it for your case
This way gives you more flexibility for defining your network


supriya Naik
supriya Naik on 7 Aug 2020 at 12:42
Is this dlnetwork possible in matlab2019a ?? Because when I used this was showing an error that undefined dlnetwork
Sai Bhargav Avula
Sai Bhargav Avula on 10 Aug 2020 at 4:41
dlnetwork function was introduced in 2019b. Hence you are getting this error. Upgrade the MATLAB to atleast 2019b to use dlnetwork

Sign in to comment.

Translated by