I have trained a Deep Neural architecture for regression problem and after the hundred's of epochs, model predicting the same output for both training and testing data.

When I reduced the batch size, atleast I'm not getting the same value for all the samples.

According to me reasons could be, model is not getting trained and gradient died in between. If it's correct, Im not sure why it's happening in my case where I have just "3 CNN + 3 DNN" layers on my architecture.

  1. Using ReLu as an activation function, changing to LeakyRelu will be beneficial?
  2. How batch size contributing on it?
  3. Any other probable reason for this problem.


  • $\begingroup$ Hi vipin, when you say predicting same outputs, is the validation / training loss also not updating / decreasing? Did you perform exploratory data analysis before going into running a model? I'm asking this, because the data might also be a potential cause for this. $\endgroup$ – shepan6 Sep 7 at 8:14

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.