Getting started with TensorFlow 2 from Coursera

Welcome to this course on Getting started with TensorFlow 2!

In this course you will learn a complete end-to-end workflow for developing deep learning models with Tensorflow, from building, training, evaluating and predicting with models using the Sequential API, validating your models and including regularisation, implementing callbacks, and saving and loading 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 an image classifier deep learning 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 is intended for both users who are completely new to Tensorflow, as well as users with experience in Tensorflow 1.x.

The 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/feedforward and convolutional neural networks), activation functions, output layers, and optimisation.

What's inside

Syllabus

Introduction to TensorFlow

TensorFlow is one of the most popular libraries for deep learning, and it’s widely used today amongst researchers and professionals at all levels. In this week, you will get started with using TensorFlow on the Coursera platform and familiarise yourself with the course structure. You will also learn about some helpful resources when developing deep learning models in TensorFlow, including Google Colab. This week is really about getting everything set up, ready for diving into TensorFlow in the following week of the course.

The Sequential model API

There are multiple ways to build and apply deep learning models in TensorFlow, from high-level, quick and easy-to-use APIs, to low-level operations. In this week you will learn to use the high-level Keras API for quickly building, training, evaluating and predicting from deep learning models. The programming assignment for this week will give you the opportunity to put all this into practice and develop an image classification model from scratch on the MNIST dataset of handwritten images.

Validation, regularisation and callbacks

Model validation and selection is an essential part of developing any machine learning model development to help prevent overfitting and improve generalisation. In this week you will learn how to use a validation dataset in a training run and apply regularisation techniques to your model. You will also learn how to use callbacks to monitor performance and perform actions according to specified criteria. In the programming assignment for this week you will put model validation and regularisation into practice on the well-known Iris dataset.

Saving and loading models

As part of your deep learning model development, you will need to be able to save and load TensorFlow models, possibly according to certain criteria you want to specify. In this week you will learn how to use callbacks to save models, manual saving and loading, and options that are available when saving models, including saving weights only. In addition, you will practice loading and using pre-trained deep learning models. In the programming assignment for this week you will write flexible model saving and loading implementations for a model trained on satellite images.

Capstone Project

In this course you have learned an end-to-end workflow for developing deep learning models in Tensorflow. The Capstone Project gives you the opportunity to bring all of your knowledge together to develop a deep learning classifier on a labelled image dataset of street view house numbers.

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Taught by Dr Kevin Webster, who is known for his work with TensorFlow

Develops skills and knowledge for deep learning models in Tensorflow essential to industry

Develops knowledge of TensorFlow, which is a popular choice for deep learning

Assumes proficiency in Python, machine learning concepts, and deep learning

May require paid subscriptions or exam fees

Reviews summary

Excellent tensorflow 2 practical course

Learners say this course is designed well for students with a background in deep learning who want to learn how to use Tensorflow 2. Assignments are practical, and the capstone project is challenging but fair. The videos are clear and concise, and the instructors are knowledgeable and helpful. Overall, this course is a great resource for anyone who wants to learn how to use Tensorflow 2.

The capstone project is challenging but fair.

"Excellent Course! The project assignment provides a very good way to self-assess and see whether you really have understood the course material. It's a strong recommendation from me! "

"Provided clear and useful insight into TensorFlow 2. Before the course I had read many of the TF2 guides and tutorials. This course helped solidify my understanding of core TF concepts."

"Excellent course with thorough practical exercises and most of all I love Kevin Webster teaching style.. Definitely a go to course for anyone who has some basic Deep Learning knowlegde. "

"This course is a good complement to the courses offered by Deeplearning.ai in terms of focusing on the basic neural network coding."

"The course is really well-organized. The videos are relatively short but very clear and concise. Programming assignments are right on spot."

The instructors are knowledgeable and helpful.

"Excellent Course .. One of the best for practicing Tensorflow . Great content and well designed assignments ... GTA did a good job though sometimes the accent is not very clear"

"Really excellent course and quality of lectures and coding tutorials were beyond my expectation. I think this course is literally the best TF course available in Coursera"

"Really nice introduction to TF2. In my case, I have worked professionally with TF1 for some time, so the material was quite trivial. Nevertheless, it was still a nice refresher."

"One of the best courses that i have taken on coursera. Clearly explanation of concepts and very good labs which give data scientist clear path to train models using tensorflow 2"

"Capstone project and assignments were much more hands on than other programs like DeepLearning. AI"

"I already knew the subject, so I was able to go fast, but I really loved the completeness of this course, the approach, the tests, and the capstone project. Basically everything. Very good indeed!"

The course is well-structured and easy to follow.

"This course is a good complement to the courses offered by Deeplearning.ai in terms of focusing on the basic neural network coding."

"This course is a good starting point to explore tensorflow."

"This course had a good balance between the application-specific elements and the broader ML discipline. Good teaching and materials."

The course assignments are practical and helpful.

"Great course with great teachers. Good complement to deeplearning.ai courses from Laurence Moroney, very good as well :-)"

"This was very well explained and guided. I would love to continue learning on Artificial intelligence and data science."

"This course is terrific! All you need to start coding almost any DL model. Really good to get yourself comfortable with tensorflow."

"This class is excelent for beginers to learn tf2"

"Really amazing experience with this course perfect start after knowing the mathematical concepts of how nn works"

"I really liked this course. The pace is very good. The focus is also great."

There were some issues with the autograder.

"However, there are some drawbacks. Almost every module consists of the following components: 1. Videos where the instructor explains concepts while showing code. 2. Videos where the TA (Teaching Assistant) explains concepts while coding. 3. JupyterNotebook exercises. 1 and 2 are quite redundant. Moreover, video 2 involves typing out code from scratch instead of explaining pre-written code, which makes the videos unnecessarily long. Typing out code while watching the video was quite painful."

"In addition, the lab's automatic grading tool was a bit unstable."

The course assumes prior knowledge of deep learning.

"This is such a great course to get aquainted with TF and gain practice hands-on! Keep the courses coming!"

"This is a beautifully structured course. It does require a fair bit of preliminary knowledge in DL, but once you have that, the practical implementation in this course is on point."

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 Getting started with TensorFlow 2 with these activities:

TensorFlow Tutorial Exercises

Show steps

Reinforce TensorFlow concepts by completing guided tutorials and exercises.

Browse courses on TensorFlow

Show steps

Follow step-by-step tutorials on TensorFlow's official website.
Practice coding exercises provided in the tutorials to solidify your understanding.
Debug your code and troubleshoot any errors encountered during the exercises.

Practice building deep learning models with TensorFlow

Show steps

Practice solving problems by building and implementing deep learning models, enhancing your proficiency with TensorFlow's features and architecture.

Browse courses on TensorFlow

Show steps

Complete the hands-on coding tutorials within the course materials
Create simple deep learning models on your own, using the skills learned in the course
Seek out additional resources and tutorials to further refine your understanding and skills

Show all two activities

Career center

Learners who complete Getting started 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 data scientists and machine learning engineers to identify the right deep learning algorithms for a given problem, and they develop and implement the models. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Deep Learning Engineer

Computer Vision Engineer

Computer Vision Engineers design, develop, and deploy computer vision models. They work with data scientists and machine learning engineers to identify the right computer vision algorithms for a given problem, and they develop and implement the models. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Computer Vision Engineer

Research Scientist

Research Scientists develop new technologies and products by conducting research and experiments. Their work may involve designing and conducting experiments, analyzing data, and developing new theories and models. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Research Scientist

Natural Language Processing Engineer

Natural Language Processing Engineers design, develop, and deploy natural language processing models. They work with data scientists and machine learning engineers to identify the right natural language processing algorithms for a given problem, and they develop and implement the models. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

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

Data Scientist

Data Scientists use their knowledge of statistics, programming, and machine learning to extract insights from data. They work with data to identify patterns, trends, and anomalies, and they use this information to make recommendations and predictions. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Data Scientist

Machine Learning Engineer

Machine Learning Engineers design, develop, and deploy machine learning models. They work with data scientists to identify the right machine learning algorithms for a given problem, and they develop and implement the models. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Machine Learning Engineer

Robotics Engineer

Robotics Engineers design, develop, and deploy robots. They work with data scientists and machine learning engineers to identify the right machine learning algorithms for a given problem, and they develop and implement the models. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Robotics Engineer

Software Engineer

Software Engineers design, develop, and maintain software applications. They work with users to gather requirements, and they design and implement software solutions that meet those requirements. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Software Engineer

Data Analyst

Data Analysts use their knowledge of statistics, programming, and machine learning to extract insights from data. They work with data to identify patterns, trends, and anomalies, and they use this information to make recommendations and predictions. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Data Analyst

Business Analyst

Business Analysts use their knowledge of business and technology to identify and solve business problems. They work with stakeholders to gather requirements, and they develop and implement solutions that meet those requirements. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Business Analyst

Product Manager

Product Managers are responsible for the development and launch of new products. They work with engineers, designers, and marketers to bring products to market that meet the needs of customers. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Product Manager

Marketing Manager

Marketing Managers are responsible for the development and execution of marketing campaigns. They work with marketers to create and implement campaigns that reach target audiences and achieve marketing goals. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Marketing Manager

Sales Manager

Sales Managers are responsible for the development and execution of sales strategies. They work with sales teams to achieve sales goals and objectives. This course can help you develop the skills and knowledge necessary to be successful in this role, such as how to build and train deep learning models, how to validate and evaluate models, and how to save and load models. Additionally, the course will give you hands-on experience with TensorFlow, one of the most popular deep learning libraries.

See salaries and explore the career path for Sales Manager

Finance Manager

Finance Managers are responsible for the financial health of an organization. They work with accountants and other financial professionals to develop and implement financial strategies. This course may be useful for those who want to develop a foundation in deep learning, as it can help you understand the underlying concepts and algorithms of deep learning models.

See salaries and explore the career path for Finance Manager

Human Resources Manager

Human Resources Managers are responsible for the development and implementation of human resources policies and programs. They work with employees and managers to ensure that the organization has a skilled and motivated workforce. This course may be useful for those who want to develop a foundation in deep learning, as it can help you understand the underlying concepts and algorithms of deep learning models.

See salaries and explore the career path for Human Resources Manager