I came across this problem, and am not sure where to start. What model would work best for this problem and why?

Imagine the digits in the test set of the MNIST dataset (http://yann.lecun.com/exdb/mnist/) got cut in half vertically and shuffled around. Implement a way to restore the original test set from the two halves, whilst maximizing the overall matching accuracy.

  • $\begingroup$ What have you tried so far to solve this problem? Have you found some solution online? Share with us your findings so far. $\endgroup$
    – nbro
    Dec 18 '21 at 21:56
  • $\begingroup$ So far i have found nothing. I tried to implement resnet38 to classify each of the halves as a number, but then im not sure how to attach two 1's or two 2's. Also resent38 gives bad predictions $\endgroup$ Dec 26 '21 at 2:46

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.