Hi, Taras.
“A reasonable benchmark is to achieve over 99% accuracy for training and over 95% accuracy for validation within 15 epochs.” This seems too high for me because the task is 26 class classification.
I checked more sample images than 100.
I think shear and rotation are useless or limited gain since all images I checked are upright.
And horizontal flips will be harmful because they are all right hand.
I reflect those findings on the settings of ImageDataGenerator but my result was far beyond “A reasonable benchmark”
Any tips on how to achieve 99% accuracy in 15 epochs? Did you use transfer learning?
3 Likes