《TensorFlow 1.x機器學習》是2018年東南大學出版社出版的圖書。
基本介紹
- 書名：TensorFlow 1.x機器學習
- 作者：[越] 全華（Quan Hua），[巴] 夏姆斯·烏爾·阿齊姆（Shams，UI，Azeem），[美] 賽義夫·阿哈邁德（Saif Ahmed）
- 類別：電腦程式設計類圖書
- 出版社：東南大學出版社
- 出版時間：2018年
- 開本：16 開
- ISBN：9787564177546
內容簡介,圖書目錄,
內容簡介
Google的TensorFlow是機器學習世界的遊戲規則改變者。
《TensorFlow 1.x機器學習（影印版 英文版）》將教你如何發揮Python和TensorFlow 1.x的威力更容易地入門機器學習。首先，你將了解基礎的安裝過程並瀏覽TensorFlow 1.x的各種能力。然後是訓練和運行分類器，以及介紹庫中的特性，包括TensorBoard的數據流圖、訓練和性能可視化——全部通過一個例子展現——富含背景信息且來自多個行業的實際問題。你將進一步探索文本和圖像分析，並在TensorFlow 1.x中學習CNN建模和設定。接下來，實現一個完整的真實生產系統，從訓練到運行一個深度學習模型。逐步深入學習Amazon Web Services（AWS）並創建一個深度神經網路以解決視頻活動識別問題。*後，把caffe模型轉換到TensorFlow，並學習高級TensorFlow庫：TensorFlow—Slim。
學完《TensorFlow 1.x機器學習（影印版 英文版）》，你會被武裝成可以應對機器學習環境中任何TensorFlow 1.x相關挑戰的絕地武士。
圖書目錄
Preface
Chapter 1： Getting Started with TensorFiow
Current use
Installing TensorFIow
Ubuntu installation
macOS installation
Windows installation
Virtual machine setup
Testing the installation
Summary
Chapter 2： Your First Classifier
The key parts
Obtaining training data
Downloading training data
Understanding classes
Automating the training data setup
Additional setup
Converting images to matrices
Logical stopping points
The machine learning briefcase
Training day
Saving the model for ongoing use
Why hide the test set?
Using the classifier
Deep diving into the network
Skills learned
Summary
Chapter 3： The TensorFIow Toolbox
A quick preview
Installing TensorBoard
Incorporating hooks into our code
Handwritten digits
AlexNet
Automating runs
Summary
Chapter 4： Cats and Dogs
Revisiting notMNIST
Program configurations
Understanding convolutional networks
Revisiting configurations
Constructing the convolutional network
Fulfilment
Training day
Actual cats and dogs
Saving the model for ongoing use
Using the classifier
Skills learned
Summary
Chapter 5： Sequence to Sequence Models-Parlez-vous Fran~：ais?
A quick preview
Drinking from the firehose
Training day
Summary
Chapter 6： Finding Meaning
Additional setup
Skills learned
Summary
Chapter 7： Making Money with Machine Learning
Inputs and approaches
Getting the data
Approaching the problem
Downloading and modifying data
Viewing the data
Extracting features
Preparing for training and testing
Building the network
Training
Testing
Taking it further
Practical considerations for the individual
Skills learned
Summary
Chapter 8： The Doctor Will See You Now
The challenge
The data
The pipeline
Understanding the pipeline
Preparing the dataset
Explaining the data preparation
Training routine
Validation routine
Visualize outputs with TensorBoard
Inception network
Going further
Other medical data challenges
The ISBI grand challenge
Reading medical data
Skills Learned
Summary
Chapter 9： Cruise Control - Automation
An overview of the system
Setting up the project
Loading a pre-trained model to speed up the training
Testing the pre-trained model
Training the model for our dataset
Introduction to the Oxford-lilT Pet dataset
Dataset Statistics
Downloading the dataset
Preparing the data
Setting up input pipelines for training and testing
Defining the model
Defining training operations
Performing the training process
Exporting the model for production
Serving the model in production
Setting up TensorFIow Serving
Running and testing the model
Designing the web sewer
Testing the system
Automatic fine-tune in production
Loading the user-labeled data
Performing a fine-tune on the model
Setting up cronjob to run every day
Summary
Chapter 10： Go Live and Go Big
Quick look at Amazon Web Services
P2 instances
G2 instances
F1 instances
Pricing
Overview of the application
Datasets
Preparing the dataset and input pipeline
Pre-processing the video for training
Input pipeline with RandomShuffleQueue
Neural network architecture
Training routine with single GPU
Training routine with multiple GPU
Overview of Mechanical Turk
Summary
Chapter 11： Going Further - 21 Problems
Dataset and challenges
Problem 1 - ImageNet dataset
Problem 2 - COCO dataset
Problem 3 - Open Images dataset
Problem 4 - YouTube-8M dataset
Problem 5 - AudioSet dataset
Problem 6 - LSUN challenge
Problem 7 - MegaFace dataset
Problem 8 - Data Science Bowl 2017 challenge
Problem 9 - StarCraft Game dataset
TensorFIow-based Projects
Problem 10 - Human Pose Estimation
Problem 11 - Object Detection - YOLO
Problem 12 - Object Detection - Faster RCNN
Problem 13 - Person Detection - tensorbox
Problem 14 - Magenta
Problem 15 - Wavenet
Problem 16 - Deep Speech
Interesting Projects
Problem 17 - Interactive Deep Colorization -iDeepColor
Problem 18 - Tiny face detector
Problem 19 - People search
Problem 20 - Face Recognition - MobilelD
Problem 21 - Question answering - DrQA
Gaffe to TensorFlow
TensorFIow-Slim
Summary
Appendix： Advanced Installation
Installation
Installing Nvidia driver
Installing the CUDA toolkit
Installing cuDNN
Installing TensorFIow
Verifying TensorFIow with GPU support
Using TensorFIow with Anaconda
Summary
