This Repo implements the basic building blocks of Deep Residual Networks which is trained for Image Classification using Dogs-vs-Cats Dataset
As a Neural Network gets very deep, vanishing / exploding gradients become a huge problem. ResNet solves this by using “Skip Connections” where layer 1 output goes directly to layer N input.
The concept of “Residual Block”:
ResNet algorithm due to He et al. (2015). The implementation here also took significant inspiration and follows the structure given in the GitHub repository of Francois Chollet:
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun - Deep Residual Learning for Image Recognition (2015)