Let's say that I have a pre-trained model where the training set used to pretrain the model is very different from my training set. Let's say I unfreeze layers that have X trainable parameters. What size should the training set be with/without data augmentation for multi-class/multi-label image classification with Y number of labels?

  • 2
    $\begingroup$ Hi and welcome to this community! What's the "pretraining set"? Is it the (training) set with which the pre-trained model was pre-trained? Anyway, the question in the title does not seem to be the same as the question in the body of the post. Please, ask just one question per post, or clarify how the questions are the same. $\endgroup$ – nbro Jan 12 '20 at 2:08
  • $\begingroup$ @nbro Thank you for the welcome. I edited my post. I know the title of the question was a bit general but it would have been very long otherwise if I had explained everything in it. $\endgroup$ – user Jan 12 '20 at 10:58

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.