3
$\begingroup$

I want to use K-fold cross-validation on my dataset of images. I am reading the data (images) from a directory.

How do I use cross validation with convolutional neural network in Keras?

Improve this question
$\endgroup$
2
  • $\begingroup$ You might find that data generation (slightly modifying your data to increase your dataset) produces better results than k-fold cross-validation, particularly with images. The only trick is you have to make sure your modifications don't change the labels. $\endgroup$
    – Adrian Keister
    Sep 12 '18 at 15:48
  • 1
    $\begingroup$ I tried ImageDataGenerator and I want to try k-fold cross-validation to see its results. $\endgroup$
    – Noran
    Sep 12 '18 at 18:31

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.