Attention based CNN for Image Classification

Implementing a deep learning attention based classification model proposed in the paper "Learn To Pay Attention" published in ICLR 2018 conference. The basic idea behind attention models is to focus on that parts of a problem which are important. Such a model was introduced in 2014 and was mainly focused on solving NLP problem but eventually was found to be useful in the field of computer vision. Jetley et.al in the paper "Learn To Pay Attention" used attention based mechanism to solve simple image classification problem. The most important concept discused in this paper would be'attention maps' which is a scalar matrix that represents activations of different locations of an image with respect to a target. With the help of attention maps the CNNs will eventually learn which part of an image is important for a particaular task.