I'm writing Python code to predict fetal head circumference 10mm range using classification. The model will train to classify a fetal head image into a range (e.g., 50–60 mm) representing its circumference.

But for some reason, the loss always stays at 3.5 and I'm not sure what approach might help get better results.

Link to notebook

  • 1
    $\begingroup$ Is there a reason you don’t want to predict the head size itself? $\endgroup$
    – Dave
    Feb 6 at 9:04


Your Answer

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