Introduction to TensorFlow
This course is focused on using the flexibility and “ease of use” of TensorFlow 2.x and Keras to build, train, and deploy machine learning models. You will learn about the TensorFlow 2.x API hierarchy and will get to know the main components of TensorFlow through hands-on exercises. We will introduce you to working with datasets and feature columns. You will learn how to design and build a TensorFlow 2.x input data pipeline. You will get hands-on practice loading csv data, numPy arrays, text data, and images using tf.Data.Dataset. You will also get hands-on practice creating numeric, categorical, bucketized, and hashed feature columns. We will introduce you to the Keras Sequential API and the Keras Functional API to show you how to create deep learning models. We’ll talk about activation functions, loss, and optimization. Our Jupyter Notebooks hands-on labs offer you the opportunity to build basic linear regression, basic logistic regression, and advanced logistic regression machine learning models. You will learn how to train, deploy, and productionalize machine learning models at scale with Cloud AI Platform.
What you'll learn
This course is focused on using the flexibility and “ease of use” of TensorFlow 2.x and Keras to build, train, and deploy machine learning models. You will learn about the TensorFlow 2.x API hierarchy and will get to know the main components of TensorFlow through hands-on exercises. We will introduce you to working with datasets and feature columns. You will learn how to design and build a TensorFlow 2.x input data pipeline. You will get hands-on practice loading csv data, numPy arrays, text data, and images using tf.Data.Dataset. You will also get hands-on practice creating numeric, categorical, bucketized, and hashed feature columns. We will introduce you to the Keras Sequential API and the Keras Functional API to show you how to create deep learning models. We’ll talk about activation functions, loss, and optimization. Our Jupyter Notebooks hands-on labs offer you the opportunity to build basic linear regression, basic logistic regression, and advanced logistic regression machine learning models. You will learn how to train, deploy, and productionalize machine learning models at scale with Cloud AI Platform.
Table of contents
- Introduction to Tensorflow 7m
- TensorFlow API Hierarchy 5m
- Components of TensorFlow: Tensors and Variables 9m
- Lab Intro Introduction to Tensors and Variables 1m
- Getting Started With GCP And Qwiklabs 4m
- Lab: Introduction to Tensors and Variables 0m
- Lab Intro Writing low-level TensorFlow programs 1m
- Lab: Writing Low-Level TensorFlow Code 0m
- Introduction to TensorFlow: Readings 0m
- Overview 4m
- Working in-memory and with files 4m
- Getting the data ready for model training 6m
- Lab Intro Load CSV and Numpy Data 0m
- Lab: Load CSV, Numpy, and Text data in TensorFlow 0m
- Lab Intro Loading Image Data 1m
- Lab: Loading images Using tf.Data.Dataset 0m
- Lab Intro Feature Columns 1m
- Lab: Introduction to Feature Columns 0m
- Optional Lab Intro TFRecord and tf.Example 1m
- Lab: TFRecord and tf.Example 0m
- Training on Large Datasets with tf.data API 5m
- Lab Intro Manipulating data with Tensorflow Dataset API 1m
- Lab: TensorFlow Dataset API 0m
- Optional Lab Intro Feature Analysis Using TensorFlow Data Validation and Facets 2m
- Lab: Feature Analysis Using TensorFlow Data Validation and Facets 0m
- Design and Build a TensorFlow Input Data Pipeline: Readings 0m
- Overview 1m
- Activation functions 9m
- Activation functions: Pitfalls to avoid in Backpropagation 6m
- Neural Networks with Keras Sequential API 8m
- Lab intro Keras Sequential API 0m
- Lab: Introducing the Keras Sequential API 0m
- Lab Intro Logistic Regression 1m
- Lab: [ML on GCP C3] Basic Introduction to Logistic Regression 0m
- Lab Intro Optional Lab Advanced Logistic Regression in TensorFlow 2.0 1m
- Lab: Advanced Logistic Regression in TensorFlow 0m
- Training neural networks with Tensorflow 2 and the Keras Sequential API: Readings 0m
- Neural Networks with Keras Functional API 10m
- Regularization: The Basics 5m
- Regularization: L1, L2, and Early Stopping 5m
- Regularization: Dropout 5m
- Serving models in the Cloud 3m
- Lab intro Keras Functional API 1m
- Lab: Introducing the Keras Functional API 0m
- Training neural networks with Tensorflow 2 and Keras Functional API: Readings 0m
