All the models were trained with the same configuration, using for 1000 epochs with 20 steps per , providing at each step of an epoch for both training and validation, with a reduced mini-batch size of 32 images, . The learn rate was set at {{val|1e-5}}0.00001, and dropout rate was set at {{val|1e-5}}0.4 for all models. Patience for early stopping was set at 100 epochs. The training images were further augmented with random zoom, shift and, rotation in order to improve model robustness on validation and test subsets and prevent the risk of overfitting.