I've implemented a small, basic CNN for this task of classification. Images have been resized to a convenient shape, with their colors stripped off. I've added measures to take care of the small amount of data as well as the variations in it; using batch normalization, low learning rates.
In addition to this, I've also used a class-balanced error while training (to account for the class imbalance).
Using the classifier at my end, I achieved a test accuracy of 86.55% and no over-fitting.
Addresses issue https://github.com/FreeUKGen/SummerOfCodeImages/issues/2
I've implemented a small, basic CNN for this task of classification. Images have been resized to a convenient shape, with their colors stripped off. I've added measures to take care of the small amount of data as well as the variations in it; using batch normalization, low learning rates.
In addition to this, I've also used a class-balanced error while training (to account for the class imbalance). Using the classifier at my end, I achieved a test accuracy of 86.55% and no over-fitting.