2
$\begingroup$

Number of labels: 1000, Dataset size: 200000 images Final probability for 1000 labels is in the range of 0.3 to 0.34. I was expecting large variation in probabilities. Can someone tell me what I am doing wrong. I am following this tutorial

$\endgroup$
  • $\begingroup$ Could you elaborate on what you mean by score here? $\endgroup$ – Nischal Hp Jan 3 '18 at 6:09
  • $\begingroup$ By score I mean probability $\endgroup$ – Ravikrn Jan 3 '18 at 8:11
  • $\begingroup$ Probability of what? The highest probability for the corresponding class? The probability for one specific class? $\endgroup$ – Jan van der Vegt Jan 3 '18 at 8:44
  • $\begingroup$ Probability of each class $\endgroup$ – Ravikrn Jan 3 '18 at 11:59
2
$\begingroup$

In my experience, the example code for a low number of classes (<200) works well. When moving to more classes the imbalance data makes the network converge to the same numbers. You have imbalance data because now each output is a binary classifier by its own, this doesn't happen with softmax. The way to mitigate the problem is to use weighted_cross_entropy_with_logits and set pos_weight to a positive number > 1 (10 works). But I still don't get very good results.

| improve this answer | |
$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.