I am getting different accuracy after each run in DNN.

6 次查看（过去 30 天）

显示更早的评论

krishna Chauhan 2020-6-25

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/554458-i-am-getting-different-accuracy-after-each-run-in-dnn

评论： krishna Chauhan 2020-8-25

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 个评论
显示 6更早的评论隐藏 6更早的评论

krishna Chauhan 2020-6-26

I cant attach the whole data its above 5MB. The example I followed was this

https://in.mathworks.com/help/wavelet/examples/spoken-digit-recognition-with-wavelet-scattering-and-deep-learning.html

second part using CNN.

krishna Chauhan 2020-6-27

code_matlab.zip

Sir kindly find the attachement.I have not included the data folder.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Aditya Patil 2020-8-19

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/554458-i-am-getting-different-accuracy-after-each-run-in-dnn#answer_482012

Set a random seed using the rng function. Otherwise, during each run, a different random seed might be selected, resulting in different results.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

krishna Chauhan 2020-8-25

I did that too before trainNetwork()

But still the problem is same

请先登录，再进行评论。

请先登录，再回答此问题。

类别

MATLAB Installation and Licensing Install Products

在 Help Center 和 File Exchange 中查找有关 Install Products 的更多信息

标签

Community Treasure Hunt

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

Translated by