MATLAB Answers

I am getting different accuracy after each run in DNN.

11 views (last 30 days)
krishna Chauhan
krishna Chauhan on 25 Jun 2020
Commented: krishna Chauhan on 25 Aug 2020
Hello there
I am using a simple DNN architecture , with 24 layers in total, containing CNN and classification layer only. for 10 epochs I am getting a diffrent accuracy every time is it possible. Also the traing graph is not settled till end of training, I tried for 50 epochs too.
any help?

  8 Comments

Show 5 older comments
krishna Chauhan
krishna Chauhan on 26 Jun 2020
okay sir I will try. Meanwhile is there any way to run the code over google colab or some other plateform as I get an optimum answer that if I go for say 1000 epochs may be the result will be stable. Currently i was exceuting the code for 10epochs only.
krishna Chauhan
krishna Chauhan on 27 Jun 2020
Sir kindly find the attachement.I have not included the data folder.

Sign in to comment.

Answers (1)

Aditya Patil
Aditya Patil on 19 Aug 2020
Set a random seed using the rng function. Otherwise, during each run, a different random seed might be selected, resulting in different results.

  1 Comment

krishna Chauhan
krishna Chauhan on 25 Aug 2020
I did that too before trainNetwork()
But still the problem is same

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!