This repository was archived by the owner on Oct 5, 2019. It is now read-only.
The use of data augmentation #2
Comments
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
From what I see, you got, on average, 51 faces per member (some are more and some are less). Have you considered the use of data augmentation to increase the number of data and/or balance out the training set?
The text was updated successfully, but these errors were encountered: