caprioGirl

yes i figured much, that it's because of the miscellaneous type. I am using whole of CoNSeP training data just like in the paper, so I am confused why is...

@simongraham Here is the misc graph from tensorboard. 

am i missing something in the classification pipeline?? @simongraham More insight onto the training details are as follows: 1. extract patches: 540x540_80x80, all of train, and test as validation, original...