Baranwal, Ajay
QRcode
자료유형 | E-BOOK |
---|---|
서명/저자사항 | What's New in TensorFlow 2. 0 [electronic resource] : Use the New and Improved Features of TensorFlow to Enhance Machine Learning and Deep Learning. |
개인저자 | Baranwal, Ajay. Khatri, Alizishaan, Baranwal, Tanish, |
발행사항 | Birmingham: Packt Publishing, Limited, 2019. |
형태사항 | 1 online resource (192 p.). |
기타형태 저록 | Print version: Baranwal, Ajay What's New in TensorFlow 2. 0 : Use the New and Improved Features of TensorFlow to Enhance Machine Learning and Deep Learning Birmingham : Packt Publishing, Limited,c2019 9781838823856 |
ISBN | 1838828834 9781838828837 |
일반주기 |
Description based upon print version of record.
Manually saving and restoring weights |
내용주기 | Cover; Title Page; Copyright and Credits; Contributors; About Packt; Table of Contents; Preface; Section 1: TensorFlow 2.0 -- Architecture and API Changes; Chapter 1: Getting Started with TensorFlow 2.0; Technical requirements; What's new?; Changes from TF 1.x; TF 2.0 installation and setup; Installing and using pip; Using Docker; GPU installation; Installing using Docker; Installing using pip; Using TF 2.0; Rich extensions; Ragged Tensors; What are Ragged Tensors, really?; Constructing a Ragged Tensor; Basic operations on Ragged Tensors; New and important packages; Summary Chapter 2: Keras Default Integration and Eager ExecutionTechnical requirements; New abstractions in TF 2.0; Diving deep into the Keras API; What is Keras?; Building models; The Keras layers API; Simple model building using the Sequential API; Advanced model building using the functional API; Training models; Saving and loading models; Loading and saving architecture and weights separately; Loading and saving architectures; Loading and saving weights; Saving and loading entire models; Using Keras; Using the SavedModel API; Other features; The keras.applications module The keras.datasets moduleAn end-to-end Sequential example; Estimators; Evaluating TensorFlow graphs; Lazy loading versus eager execution; Summary; Section 2: TensorFlow 2.0 -- Data and Model Training Pipelines; Chapter 3: Designing and Constructing Input Data Pipelines; Technical requirements; Designing and constructing the data pipeline; Raw data; Splitting data into train, validation, and test data; Creating TFRecords; TensorFlow protocol messages -- tf.Example; tf.data dataset object creation; Creating dataset objects; Creating datasets using TFRecords Creating datasets using in-memory objects and tensorsCreating datasets using other formats directly without using TFRecords; Transforming datasets; The map function; The flat_map function; The zip function; The concatenate function; The interleave function; The take(count) function; The filter(predicate) function; Shuffling and repeating the use of tf.data.Dataset; Batching; Prefetching; Validating your data pipeline output before feeding it to the model; Feeding the created dataset to the model; Examples of complete end-to-end data pipelines; Creating tfrecords using pickle files Best practices and the performance optimization of a data pipeline in TF 2.0Built-in datasets in TF 2.0; Summary; Further reading; Chapter 4: Model Training and Use of TensorBoard; Technical requirements; Comparing Keras and tf.keras; Comparing estimator and tf.keras; A quick review of machine learning taxonomy and TF support; Creating models using tf.keras 2.0; Sequential APIs; Functional APIs; Model subclassing APIs; Model compilation and training; The compile() API; The fit() API; Saving and restoring a model; Saving checkpoints as the training progresses |
요약 | This book will cover all the new features that have been introduced in TensorFlow 2.0 especially the major highlight, including eager execution and more. You will learn how to make the best use of these features to migrate your codes from TensorFlow 1.x to TensorFlow 2.0 in a seamless way. |
일반주제명 | Open source software. Machine learning. Machine learning. Open source software. |
언어 | 영어 |
바로가기 | URL |
서평 (0 건)
*주제와 무관한 내용의 서평은 삭제될 수 있습니다.
서평추가