About this course: We introduce low-level TensorFlow and work our way through the necessary concepts and APIs so as to be able to write distributed machine learning models. Given a TensorFlow model, we explain how to scale out the training of that model and offer high-performance predictions using Cloud Machine Learning Engine. Course Objectives: Create machine learning models in TensorFlow Use the TensorFlow libraries to solve numerical problems Troubleshoot and debug common TensorFlow code pitfalls Use tf.estimator to create, train, and evaluate an ML model Train, deploy, and productionalize ML models at scale with Cloud ML Engine
Who is this class for: This course is aimed at data scientists, data engineers and programmers interested in learning how to apply machine learning in practice.
Created by: Google Cloud
| Basic Info | Course 3 of 5 in the Machine Learning with TensorFlow on Google Cloud Platform Specialization |
| Level | Intermediate |
| Commitment | 1 week of study, 8-10 hours/week |
| Language | English |
| Hardware Req | You'll need to use a desktop web browser to access labs. |
| How To Pass | Pass all graded assignments to complete the course. |
| User Ratings |
Preview
Syllabus
WEEK 1
Introduction
The tool we will use to write machine learning programs is TensorFlow and so in this course, we will introduce you to TensorFlow. In the first course, you learned how to formulate business problems as machine learning problems and in the second course, you learned how machine works in practice and how to create datasets that you can use for machine learning. Now that you have the data in place, you are ready to get started writing machine learning programs.
3 videos
- Video: Lab Overview
- LTI Item: Qwiklabs – Getting Started with Google Cloud Platform and Qwiklabs
- Video: Lab Review
Core TensorFlow
We will introduce you to the core components of TensorFlow and you will get hands-on practice building machine learning programs. You will compare and write lazy evaluation and imperative programs, work with graphs, sessions, variables, as finally debug TensorFlow programs.
19 videos
- Video: What is TensorFlow
- Video: Benefits of a Directed Graph
- Video: TensorFlow API Hierarchy
- Video: Lazy Evaluation
- Discussion Prompt: Importance of an API hierarchy
- Video: Graph and Session
- Video: Evaluating a Tensor
- Video: Visualizing a graph
- Video: Tensors
- Video: Variables
- Discussion Prompt: Variables and Placeholder
- Video: Lab Intro: Writing low-level TensorFlow programs
- Video: Lab Solution
- Video: Introduction
- Video: Shape problems
- Video: Fixing shape problems
- Video: Data type problems
- Video: Debugging full programs
- Video: Intro: Debugging full programs
- Video: Demo: Debugging Full Programs
Graded: What is TensorFlow?
Graded: Graphs and Sessions
Graded: Qwiklabs – Writing low-level TensorFlow programs
Graded: Core TensorFlow
WEEK 2
Estimator API
In this module we will walk you through the Estimator API.
18 videos
- Video: Estimator API
- Video: Pre-made Estimators
- Video: Demo: Housing Price Model
- Video: Checkpointing
- Video: Training on in-memory datasets
- Video: Lab Intro: Estimator API
- Video: Lab Solution: Estimator API
- Video: Train on large datasets with Dataset API
- Video: Lab Intro: Scaling up TensorFlow ingest using batching
- Video: Lab Solution: Scaling up TensorFlow ingest using batching
- Video: Big jobs, Distributed training
- Video: Monitoring with TensorBoard
- Video: Demo: TensorBoard UI
- Video: Serving Input Function
- Video: Recap: Estimator API
- Video: Lab Intro: Creating a distributed training TensorFlow model with Estimator API
- Video: Lab Solution: Creating a distributed training TensorFlow model with Estimator API
Graded: Qwiklabs – Lab Estimator API
Graded: Qwiklabs – Scaling up TensorFlow ingest using batching
Graded: Qwiklabs – Creating a distributed training TensorFlow model with Estimator API
Graded: Estimator API
WEEK 3
Scaling TensorFlow models with CMLE
I’m here to talk about how you would go about taking your TensorFlow model and training it on GCP’s managed infrastructure for machine learning model training and deployed.
6 videos
- Video: Why Cloud Machine Learning Engine?
- Video: Train a Model
- Video: Monitoring and Deploying Training Jobs
- Video: Lab Intro: Scaling TensorFlow with Cloud Machine Learning Engine
- Video: Lab Solution: Scaling TensorFlow with Cloud Machine Learning Engine
Graded: Qwiklabs – Scaling TensorFlow with Cloud Machine Learning Engine
Graded: Cloud MLE
Summary
Here we summarize the TensorFlow topics we covered so far in this course. We'll revisit core TensorFlow code, the Estimator API, and end with scaling your machine learning models with Cloud Machine Learning Engine.
1 video
FAQs
How It Works
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Certificates
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
Creators
Google Cloud
We help millions of organizations empower their employees, serve their customers, and build what’s next for their businesses with innovative technology created in—and for—the cloud. Our products are engineered for security, reliability, and scalability, running the full stack from infrastructure to applications to devices and hardware. Our teams are dedicated to helping customers apply our technologies to create success.
Pricing
| Purchase Course | |
|---|---|
| Access to course materials | Available |
| Access to graded materials | Available |
| Receive a final grade | Available |
| Earn a shareable Course Certificate | Available |
Ratings and Reviews
Coursera provides universal access to the world’s best education,
partnering with top universities and organizations to offer courses online.
© 2018 Coursera Inc. All rights reserved.
Good & Nice course for Data Engineering