Explore

Advanced Deployment Scenarios with TensorFlow

Approx. 13 hours to complete

Save Course

Go to Course

Course Summary

Learn how to deploy TensorFlow models in advanced scenarios such as distributed training, serving models through REST APIs, and scaling models to handle large amounts of data.

Key Learning Points

Deploy TensorFlow models in advanced scenarios
Understand distributed training
Serve models through REST APIs
Scale models to handle large amounts of data

Job Positions & Salaries of people who have taken this course might have

Machine Learning Engineer
- USA: $112,000
- India: ₹2,000,000
- Spain: €40,000
Data Scientist
- USA: $98,000
- India: ₹1,800,000
- Spain: €35,000
Artificial Intelligence Architect
- USA: $150,000
- India: ₹3,000,000
- Spain: €60,000

Learning Outcomes

Learn how to deploy TensorFlow models in advanced scenarios
Understand distributed training and how to scale models to handle large amounts of data
Serve models through REST APIs

Prerequisites or good to have knowledge before taking this course

Basic knowledge of TensorFlow
Familiarity with machine learning concepts

Course Difficulty Level

Advanced

Course Format

Online
Self-paced
Video lectures

Similar Courses

Machine Learning Engineering for Production (MLOps) Specialization
Scalable Machine Learning on Big Data using Apache Spark

Related Education Paths

Related Books

Description

Bringing a machine learning model into the real world involves a lot more than just modeling. This Specialization will teach you how to navigate various deployment scenarios and use data more effectively to train your model.

In this final course, you’ll explore four different scenarios you’ll encounter when deploying models. You’ll be introduced to TensorFlow Serving, a technology that lets you do inference over the web. You’ll move on to TensorFlow Hub, a repository of models that you can use for transfer learning. Then you’ll use TensorBoard to evaluate and understand how your models work, as well as share your model metadata with others. Finally, you’ll explore federated learning and how you can retrain deployed models with user data while maintaining data privacy. This Specialization builds upon our TensorFlow in Practice Specialization. If you are new to TensorFlow, we recommend that you take the TensorFlow in Practice Specialization first. To develop a deeper, foundational understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.

Knowledge

Use TensorFlow Serving to do inference over the web
Navigate TensorFlow Hub, a repository of models that you can use for transfer learning
Evaluate how your models work and share model metadata using TensorBoard
Explore federated learning and how to retrain deployed models while maintaining data privacy

Outline

TensorFlow Extended
Introduction, A conversation with Andrew Ng
Introduction
Serving
Installing TF Serving
TensorFlow Serving summary
Setup for serving
Serving
Predictions
Passing data to serving
Getting the predictions back
Running the colab
Complex model
Downloading the Ungraded Labs and Programming Assignments
Installation link
TF server running in colab
Serving with Fashion MNIST
Ungraded Assignment - Serving with MNIST

Sharing pre-trained models with TensorFlow Hub
Introduction, A conversation with Andrew Ng
Introduction to TF Hub
Transfer learning
Inference
Module storage
Text based models
Word embeddings
Experimenting with embeddings
Colab
Classify cats and dogs
Transfer learning
Tensorflow Hub link
Link to saved models
Colab
Pre-trained Word Embeddings
Text Classification Colab
MobileNet model details
Colab

Tensorboard: tools for model training
Introduction, A conversation with Andrew Ng
Tensorboard scalars
Callbacks
Histograms
Publishing model details
Local tensorboard
Looking at graphics in a dataset
More than one image
Confusion matrix
Multiple callbacks
tensorboard.dev
Colab
Week 3 Quiz

Federated Learning
Introduction, A conversation with Andrew Ng
Training on mobile devices
Data at the edge
How it works
Maintaining user privacy
Masking
APIs for Federated Learning
Example of federated learning
Outro
Colab
What next?
(Optional) Opportunity to Mentor Other Learners
Week 4 Quiz

Summary of User Reviews

Discover advanced deployment scenarios for TensorFlow with this course on Coursera. Users generally rave about the comprehensive nature of the course and its helpfulness in building real-world applications. One key aspect users found particularly good was the hands-on approach to learning, allowing them to apply what they learned in practical settings.

Pros from User Reviews

Comprehensive course content
Hands-on approach to learning
Helpful for building real-world applications
Great for advanced deployment scenarios

Cons from User Reviews

May be too advanced for beginners
Some users found the course challenging
Not a lot of support available during the course
Some users found the course too theoretical

Recommended for you

Deep Learning with Python - Novice to Pro!

Practical recipes on Neural Network modeling, Reinforcement & Transfer Learning using Python's Deep Learning tools Deep Learning is revolutionizing a wide range of industries....

Save Course

Symfony 4 & 5 Web Development Guide: Beginner To Advanced

Master Symfony PHP framework: from theory, through simple crud app, up to creating an advanced Real Life Application Welcome to the best course of Symfony (incl....

Save Course

Terraform with AWS - Zero to Hero (2020)

Master Terraform with AWS - Mutiple Real Projects Handson(12 Hours) VPC,EC2,ECS,ECR,Lambda,APIGateway,ALB,IAC,Fargate Terraform is one of the most popular infrastructure as code tools available in the market....

Save Course

DeepLearning.AI TensorFlow Developer Professional Certificate

TensorFlow is one of the most in-demand and popular open-source deep learning frameworks available today. The DeepLearning. Ready to deploy your models to the world?...

Save Course