Customising your models with TensorFlow 2 from Coursera

Welcome to this course on Customising your models with TensorFlow 2!

In this course you will deepen your knowledge and skills with TensorFlow, in order to develop fully customised deep learning models and workflows for any application. You will use lower level APIs in TensorFlow to develop complex model architectures, fully customised layers, and a flexible data workflow. You will also expand your knowledge of the TensorFlow APIs to include sequence models.

You will put concepts that you learn about into practice straight away in practical, hands-on coding tutorials, which you will be guided through by a graduate teaching assistant. In addition there is a series of automatically graded programming assignments for you to consolidate your skills.

At the end of the course, you will bring many of the concepts together in a Capstone Project, where you will develop a custom neural translation model from scratch.

TensorFlow is an open source machine library, and is one of the most widely used frameworks for deep learning. The release of TensorFlow 2 marks a step change in the product development, with a central focus on ease of use for all users, from beginner to advanced level.

This course follows on directly from the previous course Getting Started with TensorFlow 2. The additional prerequisite knowledge required in order to be successful in this course is proficiency in the python programming language, (this course uses python 3), knowledge of general machine learning concepts (such as overfitting/underfitting, supervised learning tasks, validation, regularisation and model selection), and a working knowledge of the field of deep learning, including typical model architectures (MLP, CNN, RNN, ResNet), and concepts such as transfer learning, data augmentation and word embeddings.

What's inside

Syllabus

The Keras functional API

TensorFlow offers multiple levels of API for constructing deep learning models, with varying levels of control and flexibility. In this week you will learn to use the functional API for developing more flexible model architectures, including models with multiple inputs and outputs. You will also learn about Tensors and Variables, as well as accessing and using inner layers within a model. The programming assignment for this week will put these techniques this into practice with a transfer learning application on the dogs and cats image dataset.

Data Pipeline

A flexible and efficient data pipeline is one of the most essential parts of deep learning model development. In this week you will learn a powerful workflow for loading, processing, filtering and even augmenting data on the fly using tools from Keras and the tf.data module. In the programming assignment for this week you will apply both sets of tools to implement a data pipeline for the LSUN and CIFAR-100 datasets.

Sequence Modelling

Sequence modelling tasks represent a rich and interesting class of problems, ranging from natural language tasks such as part-of-speech tagging and sentiment analysis, to forecasting of financial time series and speech audio generation. In this week you will learn how to use the recurrent neural network API in TensorFlow, as well as several useful layer types and tools for processing sequence data. In the programming assignment for this week, you will develop a generative language model on the Shakespeare dataset.

Model subclassing and custom training loops

For more advanced use cases of TensorFlow, it is possible to obtain a low level of control over the design and behaviour of your deep learning model, as well as the training loop itself. In this week you will learn how to exploit the Model and Layer subclassing API to develop fully flexible model architectures, as well as using the automatic differentiation tools in TensorFlow to implement custom training loops. In the programming assignment for this week you will implement these custom model building tools to develop a deep residual network.

Capstone Project

In this course you have learned a powerful set of tools for developing customised deep learning models, including for sequence data, and flexible data pipelines. The Capstone Project brings many of these concepts together with a task to develop a custom neural translation model from English into German.

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Suitable for those interested in machine learning, particularly TensorFlow, and with knowledge of Python programming

Focuses on customizing models and workflow, a key skill for deep learning development

Involves practical coding tutorials and programming assignments

Led by instructor with expertise in TensorFlow and deep learning

Builds upon knowledge from a previous course, requiring proficiency in Python and machine learning concepts

Requires working knowledge of deep learning, including model architectures and concepts

Reviews summary

Tensorflow 2.0 customization

learners say that Customising your models with TensorFlow 2 is a challenging yet informative course that provides a deep understanding of TensorFlow syntax. According to students, instructors present essential concepts in a concise and engaging manner with the help of insightful lecture videos. The course is well-structured, featuring timely coding tutorials and laboratory sessions that reinforce concepts learned in the lectures. Assignments are relevant and progressively challenging, culminating in a capstone project that tests students' problem-solving abilities and provides a sense of accomplishment upon completion. Overall, learners describe the course as comprehensive, rigorous, and highly recommended for those seeking advanced knowledge of TensorFlow.

Learners appreciate the relevance and practicality of the course assignments.

"The assignments followed on logically from the weekly exercises and tutorials and the capstone project for RNN encoder-decoder..."

"Great experience, excellent material...."

"Interesting course...I didn't find the videos as clear as Course 1."

Learners value the support provided by instructors and teaching assistants.

"Dr. Kevin Webster thank you."

"The high level course video are great they show the essence in a very clear and consice manner..."

"In short, take this course if you want a challenging course where you can learn TensorFlow 2 in depth."

Students find the course material engaging but difficult, requiring a strong foundation in TensorFlow.

"This course is very challenging, as require concrete understanding on tensorflow to conduct the whole project"

"The assignments are challenging but doable."

The capstone project is a challenging but rewarding experience for learners.

"Capstone Project was surprisingly difficult, but your hard work on it is a real confidence builder."

"Capstone project is quite a steep learning curve for me, and honestly, pretty difficult."

"Very well organized tour through Tensorflow 2 API, I learned a lot and enjoyed the course"

Students praise the course's logical structure, informative lectures, and helpful coding tutorials.

"The lectures are clear and the coding assignments are very relevant and practical."

"This course stays true to its name and covers important topics like designing custom models using the Model Subclassing API and using custom training loops."

"Initially I wanted to do only Probabilistic DL (3rd course)...but I learned quite a bit from other two courses as well..."

A few learners encountered technical difficulties with the course.

"The content of the instructions seems unstructued."

"The coding tutorials offered by the GTAs are neither insightful nor explanatory."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Customising your models with TensorFlow 2 with these activities:

Review Python programming basics

Show steps

Refresh your Python programming skills to ensure a strong foundation for the course, minimizing potential roadblocks.

Show steps

Review basic Python syntax and data structures
Practice writing simple Python programs

Join a study group to work on course assignments

Show steps

Collaborate with peers in a study group to work on course assignments, strengthening your understanding through discussion and teamwork.

Show steps

Identify peers who are interested in forming a study group
Set regular meeting times and create a shared workspace
Work together to complete assignments and prepare for exams

Explore the TensorFlow Model Garden

Show steps

Explore the TensorFlow Model Garden to discover pre-trained models and learn how to apply them to your own projects, expanding your knowledge of real-world applications of TensorFlow.

Browse courses on Pre-Trained Models

Show steps

Browse the TensorFlow Model Garden and identify relevant models
Follow tutorials to implement pre-trained models in your own projects
Experiment with different pre-trained models to optimize results

Five other activities

Expand to see all activities and additional details

Show all eight activities

Work through TensorFlow tutorials on data pipelines

Show steps

Enhance your data handling skills by working through TensorFlow tutorials on data pipelines, gaining proficiency in data loading, transformation, and augmentation techniques.

Browse courses on TensorFlow

Show steps

Review TensorFlow's data pipeline API
Implement data pipelines for real-world datasets
Experiment with different data augmentation techniques

Complete practice exercises on sequence modelling

Show steps

Enhance your understanding of sequence modelling techniques by completing practice exercises, deepening your knowledge of LSTM and GRU networks.

Browse courses on Sequence Modelling

Show steps

Review concepts of sequence modelling
Implement LSTM and GRU networks in TensorFlow
Apply sequence modelling to real-world datasets

Build a residual network from scratch

Show steps

Build a residual network from scratch using the knowledge acquired in the course to solidify your understanding of advanced deep learning model architectures.

Browse courses on Residual Networks

Show steps

Design the residual network architecture
Implement the residual network using TensorFlow 2
Train the residual network on a dataset
Evaluate the performance of the residual network

Write a blog post about your experience with TensorFlow 2

Show steps

Share your experience with TensorFlow 2 by writing a blog post that highlights the key concepts you learned, the challenges you faced, and the projects you built. This will help you solidify your understanding and potentially assist other learners.

Browse courses on TensorFlow 2

Show steps

Brainstorm ideas and outline the blog post
Write the first draft of the blog post
Edit and revise the blog post
Publish the blog post and promote it

Contribute to an open-source TensorFlow project

Show steps

Gain practical experience and contribute to the TensorFlow community by participating in an open-source project, applying your skills to real-world scenarios.

Browse courses on TensorFlow

Show steps

Identify a suitable TensorFlow open-source project
Review the project's documentation and codebase
Make contributions to the project
Collaborate with project maintainers

Career center

Learners who complete Customising your models with TensorFlow 2 will develop knowledge and skills that may be useful to these careers:

Deep Learning Engineer

Deep Learning Engineers design, develop, and deploy deep learning models. They work with a variety of data sources and deep learning algorithms. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Deep Learning Engineer.

See salaries and explore the career path for Deep Learning Engineer

Machine Learning Engineer

Machine Learning Engineers design, develop, and deploy machine learning models. They work with a variety of data sources and machine learning algorithms. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Machine Learning Engineer.

See salaries and explore the career path for Machine Learning Engineer

Machine Learning Researcher

Machine Learning Researchers design, develop, and evaluate machine learning algorithms. They work with a variety of data sources and machine learning techniques. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Machine Learning Researcher.

See salaries and explore the career path for Machine Learning Researcher

Data Engineer

Data Engineers design, develop, and implement data pipelines. They work with a variety of data sources and data engineering techniques. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Data Engineer.

See salaries and explore the career path for Data Engineer

Software Engineer

As a Software Engineer, you'll design, develop, implement, and maintain software systems. You'll work with a variety of programming languages and technologies. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Software Engineer.

See salaries and explore the career path for Software Engineer

Data Scientist

Data Scientists use data to solve business problems. They work with a variety of data sources and data analysis techniques. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Data Scientist.

See salaries and explore the career path for Data Scientist

Quantitative Analyst

Quantitative Analysts use mathematical and statistical models to analyze financial data. They work with a variety of data sources and quantitative analysis techniques. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Quantitative Analyst.

See salaries and explore the career path for Quantitative Analyst

Computer Vision Engineer

Computer Vision Engineers design, develop, and deploy computer vision models. They work with a variety of data sources and computer vision algorithms. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Computer Vision Engineer.

See salaries and explore the career path for Computer Vision Engineer

Natural Language Processing Engineer

Natural Language Processing Engineers design, develop, and deploy natural language processing models. They work with a variety of data sources and natural language processing algorithms. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Natural Language Processing Engineer.

See salaries and explore the career path for Natural Language Processing Engineer

Software Developer

Software Developers design, develop, and implement software systems. They work with a variety of programming languages and technologies. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Software Developer.

See salaries and explore the career path for Software Developer

Speech Recognition Engineer

Speech Recognition Engineers design, develop, and deploy speech recognition models. They work with a variety of data sources and speech recognition algorithms. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Speech Recognition Engineer.

See salaries and explore the career path for Speech Recognition Engineer

Data Analyst

Data Analysts use data to solve business problems. They work with a variety of data sources and data analysis techniques. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Data Analyst.

See salaries and explore the career path for Data Analyst

Operations Research Analyst

Operations Research Analysts use mathematical and statistical models to solve business problems. They work with a variety of data sources and operations research techniques. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as an Operations Research Analyst.

See salaries and explore the career path for Operations Research Analyst

Web Developer

Web Developers design, develop, and implement websites and web applications. They work with a variety of programming languages and technologies. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Web Developer.

See salaries and explore the career path for Web Developer

Business Analyst

Business Analysts use data to solve business problems. They work with a variety of data sources and business analysis techniques. This course will help you build a strong foundation in TensorFlow, one of the most widely used frameworks for deep learning. You'll learn how to develop fully customized deep learning models and workflows for any application. This will give you a competitive edge in the job market and help you succeed in your career as a Business Analyst.

See salaries and explore the career path for Business Analyst