Residual Network for Image Classification in Keras

Work from Deep learning Specialization : Course 4 : Week 2 : Assignment 1

Implemented the basic building blocks of ResNets and combined these building blocks to implement and train a state of the art neural network for hand gesture classification.

Residual Networks were introduced by He et al which allows us to train very deep neural networks.

Model Trained on SIGNS dataset shown below

Results:

Input image shape: (1, 64, 64, 3)

class prediction vector [p(0), p(1), p(2), p(3), p(4), p(5)] = [[ 1. 0. 0. 0. 0. 0.]

References:

Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun - Deep Residual Learning for Image Recognition (2015)

Francois Chollet's github repository: https://github.com/fchollet/deep-learning-models/blob/master/resnet50.py