I working on multi-label multi-class image classification. I am using TensorFlow. Currently I am using sigmoid on output layer with binary_crossentrpy. Model is giving fair accuracy, but for my requirement I need to rely on Subset accuracy (exact match) and not overall accuracy. For evaluation purpose I am using Subset Accuracy metric, but model is obviously maximizing overall accuracy. How can I add a custom loss function so that I can maximize subset accuracy.

  • $\begingroup$ You mean for a specific subset or the subset accuracy for all subsets? $\endgroup$ – Janosch Jan 17 at 9:42
  • $\begingroup$ @Janosch Look for Exact Match aka subset accuracy. Currently I am calculating subset accuracy for my test set. $\endgroup$ – Vivek Mehta Jan 17 at 9:55

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.