5 Advanced CNN Architectures


“Architecture begins when you place two bricks carefully together. There it begins.”

-- Ludwig Mies van der Rohe

Welcome to part two of this book, Image Classification and Object Detection. Part one was a foundation on neural networks architectures where we covered Multilayer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs) or Convnets for short. We wrapped up part one with strategies to structure your deep neural network projects and tune their hyperparameters to improve your network performance. In part two, we are going to build on this foundation to develop computer vision systems that solve complex image classification and object detection problems.

5.1   CNN design patterns

5.1.1   Pattern #1

5.1.2   Pattern #2

5.1.3   Pattern #3

5.2   LeNet-5

5.2.1   LeNet architecture

5.2.2   LeNet-5 implementation in Keras

5.2.3   Set up the learning hyperparameters

5.2.4   LeNet performance on MNIST dataset

5.3.1   AlexNet architecture

5.3.2   Novel features of AlexNet

5.3.3   AlexNet implementation in Keras

5.3.4   Set up the learning hyperparameters

5.3.5   AlexNet performance on CIFAR dataset

5.4   VGGNet

5.4.1   Novel features of VGGNet

5.6   ResNet