1

I am currently training a pattern classification network, and seem to get very inconsistent result.

The network seem to overfit, but the validation accuracy is very inconsistent.

I am currently trying to do pattern recognition on audio spectrograms. The audio consist of utterances of yes/no, and acoustic model (gmm-hmm) has been trained to detect these. Given i already have a gmm-hmm, I can from the alignment decode which state obervation has the highest probability, and use that as output target for my neural network.

I am currently using different network structure such as Densenet, Resnet.

I once had a run using densenet which gave me a validation accuracy of 0.8, but this seem to only have happened once. When i tries to train the network now i get validation scores around 0.3, which annoys me...

In general does it seem like the the validation score is very inconsistent, it loop around 0.2 - 0.4, which while the system keep overfitting.

Is training really supposed to be so inconsistent?..

Carlton Banks
  • 619
  • 1
  • 6
  • 26
  • Could you find a reason for your results? I am having similar issues with training fluctuating a lot in terms of validation accuracy. – Gegenwind Feb 28 '18 at 20:30
  • In order to have reproducible behavior, you need to freeze or set a constant value for certain hash-based operations. – Mirodil Apr 27 '18 at 19:53

0 Answers0