I am using feed-forward neural network for a classification task. My data is 1 million examples for 9 classes (imbalanced). Due to memory constraint in Keras, I used function generator to generate batches automatically with a batch size of 200. I trained a simple model with 3 hidden layers with ReLU activation function. Input layer is 39 dimensional MFCCs and output is 9 classes. This model worked fine when I used a subset of this huge data (Sure!) but now, while using function generator i.e model.fit_generator, I see that training accuracy is just wandering around and validation accuracy is just too low. Looks like the model is not learning at all. What might be the possible reasons for this behaviour?

about data

Data : Speech

subset of huge data mentioned was totally clean but I generated 1 million examples from 1300 examples using data augmentation techniques like equalization, time stretch, time compression, noises, reverb etc


closed as unclear what you're asking by oW_, Stephen Rauch, Djib2011, Siong Thye Goh, Sean Owen Sep 16 '18 at 2:31

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • $\begingroup$ @oW_, Stephen Rauch, Djib2011, Siong Thye Goh, Sean Owen : Could you please let me know what part of the question is unclear to you? $\endgroup$ – Mounika K.V Sep 17 '18 at 4:36