The code with an explanation is available at GitHub.

ResNet, was first introduced by Kaiming He[1]. If you are not familiar with Residual Networks and why they can more likely improve the accuracy of a network.

While creating a Sequential model in Tensor flow and Keras is not too complex, creating a residual network might have some complexities. In this article, I show you how to create a residual network from scratch.

Summary:

• Task type: classifying handwritten digits.
• Dataset: THE MNIST DATABASE
• Network Architecture: a small residual network shown in Figure 1.
• Optimizer: Adam
• Loss function: categorical_crossentropy

Code directory structure:

• main.py
• train.py
• network_model.py

#machine-learning #deep-learning #keras #tensorflow #neural-networks