0
$\begingroup$

I am trying to make a CNN model on IAM handwritten words data(which has images of words handwritten by multiple people and targets are text in the images). So, I can encode words to numbers(A=0, B=1 and so on for capital, small and punctuation). But, I couldn't quite decide on what loss to use for this problem, in tensforflow.keras.

I have found out about something called CTC loss on some repositories on GitHub. But, ctc loss was used with softmax as activation in final dense layer. And since softmax outputs probabilities for each class that sum up to 1; So, I presume softmax can't output probabilties for two "o"s at the same time.

So, what are the proper activation and loss functions that I can use for a problem like this one?

Improve this question
$\endgroup$
3
  • $\begingroup$ Why are you not treating it as a Multi-label problem? What is your end goal to predict? $\endgroup$
    – 10xAI
    Jul 7, 2020 at 7:34
  • $\begingroup$ from the definitions i know, this cannot be a multi-label problem. I may be incorrect. My end goal is to predict the text in the images, it's an ocr problem. $\endgroup$
    – Naveen Reddy Marthala
    Jul 7, 2020 at 7:47
  • $\begingroup$ So, what do you suggest I use, @10xAI $\endgroup$
    – Naveen Reddy Marthala
    Jul 7, 2020 at 11:05

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.