TensorFlow 2 Pocket Reference: Building and Deploying Machine Learning Models

This reference provides practical guidance for designing and implementing TensorFlow 2 models in Python, covering topics such as data ingestion, training, hyperparameter tuning, and model saving. It offers code snippets and best practices to help developers build efficient and effective machine learning systems.

\n Format: Paperback / softback
\n Length: 300 pages
\n Publication date: 03 August 2021
\n Publisher: O'Reilly Media, Inc, USA
\n

This comprehensive guide provides valuable insights into TensorFlow 2 design patterns in Python, empowering you to make informed decisions for diverse use cases within enterprise data science and machine learning practices. Author KC Tung delves into essential topics and tasks, offering practical guidance rather than solely focusing on TensorFlow itself. Whether you're determining when and why to feed training data using NumPy or a streaming dataset, setting up cross-validations during the training process, leveraging a pretrained model through transfer learning, or conducting hyperparameter tuning, this pocket reference serves as a valuable resource. By leveraging code snippets as templates, you can efficiently build TensorFlow models and workflows, saving valuable development time. Additionally, by integrating prebuilt models from TensorFlow Hub, you can streamline your development process and make informed design choices regarding data ingestion, training paradigms, model saving, and inference. This guide addresses common scenarios, such as model design style, data ingestion workflow, model training, and tuning, enabling you to tackle diverse TensorFlow applications with confidence and efficiency.

\n Weight: 208g\n
Dimension: 114 x 178 x 19 (mm)\n
ISBN-13: 9781492089186\n \n