1.

Record Nr.

UNINA9910483468203321

Autore

Koonce Brett

Titolo

Convolutional neural networks with Swift for Tensorflow : image recognition and dataset categorization / / Brett Koonce

Pubbl/distr/stampa

[Place of publication not identified] : , : Apress, , [2021]

©2021

ISBN

1-4842-6168-2

Edizione

[1st ed. 2021.]

Descrizione fisica

1 online resource (XXI, 245 p. 1 illus.)

Disciplina

006.32

Soggetti

TensorFlow

Neural networks (Computer science)

Data sets

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Nota di contenuto

Chapter 1: MNIST: 1D Neural Network -- Chapter 2: MNIST: 2D Neural Network -- Chapter 3: CIFAR: 2D Nueral Network with Blocks -- Chapter 4: VGG Network -- Chapter 5: Resnet 34 -- Chapter 6: Resnet 50 -- Chapter 7: SqueezeNet -- Chapter 8: MobileNrt v1 -- Chapter 9: MobileNet v2 -- Chapter 10: Evolutionary Strategies -- Chapter 11: MobileNet v3 -- Chapter 12: Bag of Tricks -- Chapter 13: MNIST Revisited -- Chapter 14: You are Here.

Sommario/riassunto

Dive into and apply practical machine learning and dataset categorization techniques while learning Tensorflow and deep learning. This book uses convolutional neural networks to do image recognition all in the familiar and easy to work with Swift language. It begins with a basic machine learning overview and then ramps up to neural networks and convolutions and how they work. Using Swift and Tensorflow, you'll perform data augmentation, build and train large networks, and build networks for mobile devices. You’ll also cover cloud training and the network you build can categorize greyscale data, such as mnist, to large scale modern approaches that can categorize large datasets, such as imagenet. Convolutional Neural Networks with Swift for Tensorflow uses a simple approach that adds progressive layers of complexity until you have arrived at the current state of the art for this field. You will:



Categorize and augment datasets Build and train large networks, including via cloud solutions Deploy complex systems to mobile devices.