This course is part of the TensorFlow 2 for Deep Learning Specialization

4.9
stars
515 ratings

Dr Kevin Webster

30,909 already enrolled

Offered By

TensorFlow 2 for Deep Learning SpecializationImperial College London

About this Course

43,645 recent views

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.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Shareable Certificate

Earn a Certificate upon completion

100% online

Start instantly and learn at your own schedule.

Course 1 of 3 in the

TensorFlow 2 for Deep Learning Specialization

Intermediate Level

Approx. 26 hours to complete

English

Flexible deadlines

Reset deadlines in accordance to your schedule.

Shareable Certificate

Earn a Certificate upon completion

100% online

Start instantly and learn at your own schedule.

Course 1 of 3 in the

TensorFlow 2 for Deep Learning Specialization

Intermediate Level

Approx. 26 hours to complete

English

Instructor

Instructor rating

4.91/5 (170 Ratings)

Dr Kevin Webster

Senior Teaching Fellow in Statistics

Faculty of Natural Sciences, Department of Mathematics

37,259 Learners

5 Courses

Offered by

Imperial College London

Imperial College London is a world top ten university with an international reputation for excellence in science, engineering, medicine and business. located in the heart of London. Imperial is a multidisciplinary space for education, research, translation and commercialisation, harnessing science and innovation to tackle global challenges.

Syllabus - What you will learn from this course

Content Rating96%(3,285 ratings)

Week1

Week 1

3 hours to complete

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.

3 hours to complete

14 videos (Total 59 min), 8 readings

14 videos

Introduction to the course2mWelcome to week 11mHello TensorFlow!1m[Coding tutorial] Hello TensorFlow!2mWhat's new in TensorFlow 24mInterview with Laurence Moroney5mIntroduction to Google Colab2m[Coding tutorial] Introduction to Google Colab8mTensorFlow documentation3mTensorFlow installation3m[Coding tutorial] pip installation3m[Coding tutorial] Running TensorFlow with Docker10mUpgrading from TensorFlow 13m[Coding tutorial] Upgrading from TensorFlow 16m

8 readings

About Imperial College & the team10mHow to be successful in this course10mGrading policy10mAdditional readings & helpful references10mWhat is TensorFlow?10mGoogle Colab resources10mTensorFlow documentation10mUpgrade TensorFlow 1.x Notebooks10m

Week2

Week 2

7 hours to complete

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.

7 hours to complete

13 videos (Total 59 min)

13 videos

Welcome to week 2 - The Sequential model API1mWhat is Keras?1mBuilding a Sequential model4m[Coding tutorial] Building a Sequential model4mConvolutional and pooling layers4m[Coding tutorial] Convolutional and pooling layers5mThe compile method5m[Coding tutorial] The compile method5mThe fit method4m[Coding tutorial] The fit method7mThe evaluate and predict methods6m[Coding tutorial] The evaluate and predict methods4mWrap up and introduction to the programming assignment1m

2 practice exercises

[Knowledge check] Feedforward and convolutional neural networks15m[Knowledge check] Optimisers, loss functions and metrics15m

Week3

Week 3

7 hours to complete

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.

7 hours to complete

11 videos (Total 60 min)

11 videos

Welcome to week 3 - Validation, regularisation and callbacks1mInterview with Andrew Ng6mValidation sets4m[Coding Tutorial] Validation sets9mModel regularisation6m[Coding Tutorial] Model regularisation4mIntroduction to callbacks5m[Coding tutorial] Introduction to callbacks7mEarly stopping and patience6m[Coding tutorial] Early stopping and patience5mWrap up and introduction to the programming assignment51s

1 practice exercise

[Knowledge check] Validation and regularisation15m

Week4

Week 4

7 hours to complete

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.

7 hours to complete

12 videos (Total 74 min)

12 videos

Welcome to week 4 - Saving and loading models1mSaving and loading model weights6m[Coding tutorial] Saving and loading model weights10mModel saving criteria4m[Coding tutorial] Model saving criteria11mSaving the entire model4m[Coding tutorial] Saving the entire model8mLoading pre-trained Keras models5m[Coding tutorial] Loading pre-trained Keras models7mTensorFlow Hub modules2m[Coding tutorial] TensorFlow Hub modules8mWrap up and introduction to the programming assignment1m

Reviews

4.9

170 reviews

5 stars
91.45%
4 stars
7.37%
3 stars
0.58%
2 stars
0.19%
1 star
0.38%

TOP REVIEWS FROM GETTING STARTED WITH TENSORFLOW 2

by AANov 21, 2021

Indeed intermediate level course. Useful course. Well designed, focussed, clutter free, comprehensive. Rare to find such course on Coursera.

by YWDec 1, 2022

The course is really well desired. I got a chance to practise all the key knowledge through the assignments. All the explanation is clear and concise.

by RSOct 21, 2020

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!

by AAMar 17, 2021

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.

View all reviews

About the TensorFlow 2 for Deep Learning Specialization

This Specialization is intended for machine learning researchers and practitioners who are seeking to develop practical skills in the popular deep learning framework TensorFlow.

The first course of this Specialization will guide you through the fundamental concepts required to successfully build, train, evaluate and make predictions from deep learning models, validating your models and including regularisation, implementing callbacks, and saving and loading models. The second course 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. The final course specialises in the increasingly important probabilistic approach to deep learning. You will learn how to develop probabilistic models with TensorFlow, making particular use of the TensorFlow Probability library, which is designed to make it easy to combine probabilistic models with deep learning. As such, this course can also be viewed as an introduction to the TensorFlow Probability library. Prerequisite knowledge for this Specialization is python 3, general machine learning and deep learning concepts, and a solid foundation in probability and statistics (especially for course 3).

Frequently Asked Questions

When will I have access to the lectures and assignments?
Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:
The course may not offer an audit option. You can try a Free Trial instead, or apply for Financial Aid.
The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
What will I get if I subscribe to this Specialization?
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.
Is financial aid available?
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.
Solve problems with Jupyter Notebooks
Jupyter Notebooks are a third-party tool that some Coursera courses use for programming assignments.
You can revert your code or get a fresh copy of your Jupyter Notebook mid-assignment. By default, Coursera persistently stores your work within each notebook.
To keep your old work and also get a fresh copy of the initial Jupyter Notebook, click File, then Make a copy.
We recommend keeping a naming convention such as “Assignment 1 - Initial” or “Copy” to keep your notebook environment organized. You can also download this file locally.
Refresh your notebook
Rename your existing Jupyter Notebook within the individual notebook view
In the notebook view, add “?forceRefresh=true” to the end of your notebook URL
Reload the screen
You will be directed to your home Learner Workspace where you’ll see both old and new Notebook files.
Your Notebook lesson item will now launch to the fresh notebook.
Find missing work
If your Jupyter Notebook files have disappeared, it means the course staff published a new version of a given notebook to fix problems or make improvements. Your work is still saved under the original name of the previous version of the notebook.
To recover your work:
Find your current notebook version by checking the top of the notebook window for the title
In your Notebook view, click the Coursera logo
Find and click the name of your previous file
Unsaved work
"Kernels" are the execution engines behind the Jupyter Notebook UI. As kernels time out after 90 minutes of notebook activity, be sure to save your notebooks frequently to prevent losing any work. If the kernel times out before the save, you may lose the work in your current session.
How to tell if your kernel has timed out:
Error messages such as "Method Not Allowed" appear in the toolbar area.
The last save or auto-checkpoint time shown in the title of the notebook window has not updated recently
Your cells are not running or computing when you “Shift + Enter”
To restart your kernel:
Save your notebook locally to store your current progress
In the notebook toolbar, click Kernel, then Restart
Try testing your kernel by running a print statement in one of your notebook cells. If this is successful, you can continue to save and proceed with your work.
If your notebook kernel is still timed out, try closing your browser and relaunching the notebook. When the notebook reopens, you will need to do "Cell -> Run All" or "Cell -> Run All Above" to regenerate the execution state.

More questions? Visit the Learner Help Center.

Getting started with TensorFlow 2

About this Course