0

I am using Theano with keras. I have a trained DNN and I have dumped the weight's in a file. I am performing some operations on these weights and again dumping the new converted weights into another file.

Now, I am loading my DNN model with these converted weights and want to compare the results between the two.

I used the keras.evaluate method but I find the accuracy to be exactly same even though the weights are different.

Is there another approach with which I can compare the accuracy?

Thanks.

blackbug
  • 1,098
  • 3
  • 13
  • 40

1 Answers1

1

Keras performs some under the hood operations for your batch_size including normalization. So if you only scaled and translated your image the result will stay the same.

Anyways you can do model.predict(sample, 1) and write your own evaluation metric to circumvent this issue.

Thomas Pinetz
  • 6,948
  • 2
  • 27
  • 46
  • I basically reduced some decimal places to lower computation load. And, now trying to figure out the loss in the accuracy due to the conversion to values with reduced decimal place. – blackbug Nov 29 '16 at 14:28