I have an image dataset of about 400 images. 70% of these data points were used for training, 15% for validation, and 15% for testing. I am using the 70% to train a CNN-based binary classifier. I augmented the training data to around 8000 images. That makes my test set really small in comparison. Is that ok, and what is considered a decent size of images for a test set?

  • $\begingroup$ Also, I am an hs student who is really new to machine learning and would appreciate any advice :) $\endgroup$ – user38639 Jul 15 '20 at 22:05
  • $\begingroup$ Depends on the complexity of the task. I know I have previously achieved high accuracy on MNIST with a similarly low amount of training data. $\endgroup$ – Recessive Jul 16 '20 at 1:16

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.