I am getting different accuracy after each run in DNN.

4 vues (au cours des 30 derniers jours)
krishna Chauhan
krishna Chauhan le 25 Juin 2020
Commenté : krishna Chauhan le 25 Août 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 commentaires
krishna Chauhan
krishna Chauhan le 26 Juin 2020
I cant attach the whole data its above 5MB. The example I followed was this
second part using CNN.
krishna Chauhan
krishna Chauhan le 27 Juin 2020
Sir kindly find the attachement.I have not included the data folder.

Connectez-vous pour commenter.

Réponses (1)

Aditya Patil
Aditya Patil le 19 Août 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 commentaire
krishna Chauhan
krishna Chauhan le 25 Août 2020
I did that too before trainNetwork()
But still the problem is same

Connectez-vous pour commenter.


En savoir plus sur Sequence and Numeric Feature Data Workflows dans Help Center et File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by