Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization

Koonce, Brett

  • 出版商: Apress
  • 出版日期: 2021-01-05
  • 售價: $1,750
  • 貴賓價: 9.5$1,663
  • 語言: 英文
  • 頁數: 240
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 1484261674
  • ISBN-13: 9781484261675
  • 相關分類: Apple DeveloperDeepLearningTensorFlow
  • 立即出貨 (庫存=1)

買這商品的人也買了...

商品描述

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.


What You'll Learn

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


Who This Book Is For
Developers with Swift programming experience who would like to learn convolutional neural networks by example using Swift for Tensorflow as a starting point.

商品描述(中文翻譯)

深入學習和應用實用的機器學習和數據集分類技術,同時學習Tensorflow和深度學習。本書使用卷積神經網絡在熟悉且易於使用的Swift語言中進行圖像識別。

本書首先提供了基本的機器學習概述,然後逐步介紹神經網絡和卷積以及它們的工作原理。使用Swift和Tensorflow,您將進行數據增強,構建和訓練大型網絡,以及為移動設備構建網絡。您還將涵蓋雲端訓練,並且您構建的網絡可以將灰度數據(例如mnist)進行分類,也可以將大型數據集(例如imagenet)進行分類。

《使用Swift for Tensorflow的卷積神經網絡》採用了一種簡單的方法,逐步增加複雜性,直到達到這一領域的最新技術水平。

您將學到什麼:

- 分類和增強數據集
- 構建和訓練大型網絡,包括使用雲端解決方案
- 將複雜系統部署到移動設備

本書適合對Swift編程有經驗的開發人員,他們希望通過使用Swift for Tensorflow作為起點,通過實例學習卷積神經網絡。

作者簡介

Brett Koonce is the CTO of Quarkworks, a mobile consulting agency. He's a developer with five years experience creating apps for iOS and Android. His team has worked on dozens of apps that are used by millions of people around the world. Brett knows the pitfalls of development and can help you avoid them. Whether you want to build something from scratch, port your app from iOS to Android (or vice versa) or accelerate your velocity, Brett can help.

作者簡介(中文翻譯)

Brett Koonce是Quarkworks的CTO,一家移動諮詢機構。他是一位有著五年經驗的開發者,專門創建iOS和Android應用程式。他的團隊已經開發了數十個被全球數百萬人使用的應用程式。Brett熟悉開發的陷阱,可以幫助您避免它們。無論您想從頭開始建立應用程式,將您的應用程式從iOS移植到Android(或反之亦然),或加快開發速度,Brett都可以提供幫助。