An orchard leaf-photo set has thousands of healthy leaves and a few blight shots. Training on the raw folders will ignore blight. Which data-prep problem is that?
Select an answer to reveal the explanation.
Short Explanation
Think of thousands of healthy-leaf photos and a few blight shots. That is class imbalance in an image set. Treat it before fitting. Raw folders are not already balanced.
Full Explanation
Class imbalance in image datasets is still a data-prep problem. Treat it before fitting. It is not a license for a combined NLP-plus-CV deep dive. Athena does not balance folders.