Back to courses

TensorFlow Developer Certificate in 2023

Learn TensorFlow. Pass the TensorFlow Developer Certificate Exam. Get Hired as a TensorFlow developer. This course will take you from a TensorFlow beginner to being part of Google's Certification Network.

instructor

Taught by: Daniel Bourke

Last updated: March 2023

Course overview

Learn TensorFlow, pass the TensorFlow Developer Certificate exam and get hired as a Machine Learning Engineer making $100,000+ a year. Taught by TensorFlow Certified Expert, Daniel Bourke, this course will take you step-by-step from an absolute beginner with TensorFlow to becoming part of Google's TensorFlow Certification Network.

What you'll learn

  • Learn to pass Google's official TensorFlow Developer Certificate exam (and add it to your resume)
  • Complete access to ALL interactive notebooks and ALL course slides as downloadable guides
  • Understand how to integrate Machine Learning into tools and applications
  • Build image recognition, text recognition algorithms with deep neural networks and convolutional neural networks
  • Applying Deep Learning for Time Series Forecasting
  • Be recognized as a top candidate for recruiters seeking TensorFlow developers
  • Build TensorFlow models using Computer Vision, Convolutional Neural Networks, and Natural Language Processing
  • Increase your skills in Machine Learning and Deep Learning
  • Learn to build all types of Machine Learning Models using the latest TensorFlow 2
  • Using real-world images in different shapes and sizes to visualize the journey of an image through convolutions to understand how a computer “sees” information, plot loss and accuracy
  • Gain the skills you need to become a TensorFlow Certified Developer

Why should I learn TensorFlow and get the TensorFlow Developer Certificate?

Here's the top 3 reasons why we think you should learn TensorFlow:

  1. Lots of jobs available: Used by major companies like Google, Airbnb, Uber, DeepMind, Intel, IBM, Twitter means there is huge job demand for TensorFlow developers. TensorFlow is outgrowing other popular ML tools like PyTorch in the job market.
  2. High demand = High salary: TensorFlow developers earn US$148,000 on average with some earning over US$200,000 according to recent statistics from ZipRecruiter.
  3. Old fashioned FUN: Learning TensorFlow allows you to build deep learning models for a range of tasks such as regression, computer vision (finding patterns in images), natural language processing (finding patterns in text) and time series forecasting (predicting future trends given a range of past events). That's pretty damn awesome!

The goal of this course is to teach you all the skills necessary for you to pass the exam and get your TensorFlow Developer Certification so you can display it on your resume, LinkedIn, Github and other social media platforms to make you stand out as a top candidate for recruiters looking for TensorFlow Developers. You'll also be part of Google's TensorFlow Developer Network where recruiters are able to find you.

And you'll be learning TensorFlow in good company.

Graduates of Zero To Mastery are now working at Google, Tesla, Amazon, Apple, IBM, Uber, Facebook, Shopify + other top tech companies.

This can be you.

By enrolling today, you’ll also get to join our exclusive live online community classroom to learn alongside thousands of students, alumni, mentors, TAs and Instructors.

Most importantly, you will be learning TensorFlow from an industry expert who is TensorFlow Certified and has real-world Machine Learning experience.

Here is a full breakdown of everything you will learn in this TensorFlow Course:

This TensorFlow course is very hands-on and project based. You won't just be staring at us teach and code. We'll leave that for other tutorials and courses.

You will actually be running experiments, doing exercises and building real-world machine learning models and projects to mimic real life scenarios.

We will also show you what the TensorFlow exam will look like for you.

By the end of it all, you will develop the skillset needed to develop modern deep learning solutions that big tech companies encounter.

Fair warning, this course is very comprehensive. But don't be intimidated, we will teach you everything from scratch!

0. TensorFlow Fundamentals

  • Introduction to tensors (creating tensors)
  • Getting information from tensors (tensor attributes)
  • Manipulating tensors (tensor operations)
  • Tensors and NumPy
  • Using @tf.function (a way to speed up your regular Python functions)
  • Using GPUs with TensorFlow

1. Neural Network Regression with TensorFlow

  • Build TensorFlow sequential models with multiple layers
  • Prepare data for use with a machine learning model
  • Learn the different components which make up a deep learning model (loss function, architecture, optimization function)
  • Learn how to diagnose a regression problem (predicting a number) and build a neural network for it

2. Neural Network Classification with TensorFlow

  • Learn how to diagnose a classification problem (predicting whether something is one thing or another)
  • Build, compile & train machine learning classification models using TensorFlow
  • Build and train models for binary and multi-class classification
  • Plot modelling performance metrics against each other
  • Match input (training data shape) and output shapes (prediction data target)

3. Computer Vision and Convolutional Neural Networks with TensorFlow

  • Build convolutional neural networks with Conv2D and pooling layers
  • Learn how to diagnose different kinds of computer vision problems
  • Learn to how to build computer vision neural networks
  • Learn how to use real-world images with your computer vision models

4. Transfer Learning with TensorFlow Part 1: Feature Extraction

  • Learn how to use pre-trained models to extract features from your own data
  • Learn how to use TensorFlow Hub for pre-trained models
  • Learn how to use TensorBoard to compare the performance of several different models

5. Transfer Learning with TensorFlow Part 2: Fine-tuning

  • Learn how to setup and run several machine learning experiments
  • Learn how to use data augmentation to increase the diversity of your training data
  • Learn how to fine-tune a pre-trained model to your own custom problem
  • Learn how to use Callbacks to add functionality to your model during training

6. Transfer Learning with TensorFlow Part 3: Scaling Up (Food Vision mini)

  • Learn how to scale up an existing model
  • Learn to how evaluate your machine learning models by finding the most wrong predictions
  • Beat the original Food101 paper using only 10% of the data

7. Milestone Project 1: Food Vision

  • Combine everything you've learned in the previous 6 notebooks to build Food Vision: a computer vision model able to classify 101 different kinds of foods. Our model well and truly beats the original Food101 paper.

8. NLP Fundamentals in TensorFlow

You'll learn to:

  • Preprocess natural language text to be used with a neural network
  • Create word embeddings (numerical representations of text) with TensorFlow
  • Build neural networks capable of binary and multi-class classification using:
    • RNNs (recurrent neural networks)
    • LSTMs (long short-term memory cells)
    • GRUs (gated recurrent units)
    • CNNs
  • Learn how to evaluate your NLP models

9. Milestone Project 2: SkimLit

  • Replicate the model which powers the PubMed 200k paper to classify different sequences in PubMed medical abstracts (which can help researchers read through medical abstracts faster)

10. Time Series fundamentals in TensorFlow

  • Learn how to diagnose a time series problem (building a model to make predictions based on data across time, e.g. predicting the stock price of AAPL tomorrow)
  • Prepare data for time series neural networks (features and labels)
  • Understanding and using different time series evaluation methods
    • MAE — mean absolute error
  • Build time series forecasting models with TensorFlow
    • RNNs (recurrent neural networks)
    • CNNs (convolutional neural networks)

11. Milestone Project 3: (Surprise)

  • If you've read this far, you are probably interested in the course. This last project will be good... we promise you, so see you inside the course ;)

What's the bottom line?

TensorFlow's growth and adoption is exploding which means more and more job openings are appearing for this specialized knowledge.

Companies like Google, Airbnb, Uber, DeepMind, Intel, IBM, Twitter, and many others are currently powered by TensorFlow. TensorFlow is even outgrowing other popular Machine Learning tools like PyTorch in the job market.

We guarantee you this is the most comprehensive online course on passing the TensorFlow Developer Certificate and qualify you as a TensorFlow expert.

So why wait? Advance your career and earn a higher salary by becoming a Google Certified Developer and adding TensorFlow to your toolkit 💪.

And you have nothing to lose. Because you can start learning right now and if this course isn't everything you expected, we'll refund you 100% within 30 days. No hassles and no questions asked.

When's the best time to get started? Today!

There's never a bad time to learn in-demand skills. But the sooner, the better. So start learning TensorFlow today by joining the ZTM Academy. You'll have a clear roadmap to developing the skills to build your own projects, get hired, and advance your career.

Start learning now
Expand Overview

What you'll build

The best way you learn is by doing. Not just watching endless tutorials. That's why a key part of this course is the real-world projects that you'll get to build. Plus they'll look great on your portfolio.

Food Vision

Food Vision

Build a deep learning computer vision to model to identify over 100 different types of food. We'll use transfer learning to take what one model has learned elsewhere and apply it to our own problem, beating previous state of the art results along the way.

SkimLit

SkimLit

Researchers do enough reading. In SkimLit (skim the literature), we'll use natural language processing (NLP) to build a model to help classify research abstracts into smaller, more understandable pieces.

BitPredict

BitPredict

Is Bitcoin going up or down tomorrow? Let's build a deep learning model to find out. We'll replicate the N-BEATS algorithm, a state of the art time series forecasting model. Note: This project is not financial advice.

start learning now

Don't just take our word for it

Our courses and community have helped 1,000s of Zero To Mastery students go from zero to getting hired to levelling up their skills and advancing their careers to new heights.

Subhabrata Nath

This course is far better than any others and this is from personal experience. I have watched lots of videos about Deep Learning, but here you'll get knowledge along with inspiration to write code as much as possible, and this is all that matters.

Subhabrata Nath

Thank you so much! This is an amazing course. I just passed my TF exam and I couldn't have done it without you. I had 3 calls for job offers today in Machine Learning roles! I would recommend this A+ course to anyone who wants to level-up and stand out.

Seth Johnson

This course is just plain amazing. Danial focuses on the code and the practical aspects of Deep Learning rather than go deep (pun intended) on the theory. His way of teaching is unparalleled, and listening to him always brings a smile to my face.

Blazey

Daniel is such an excellent instructor. I wish I found him way earlier. He built the course layer upon layer so that you have a strong foundation to understand more difficult concepts and he shows you his thought process and approach to solving problems.

Sha Brown

Excellent course! I've taken ML classes before, but it was extremely beneficial to go through this tensorflow course. This course gave me the tools and confidence to start working on reviewing datasets and allowed me to focus on understanding the data.

Krishna

Best course to practically learn Deep Learning and Tensorflow. The instructors design the course such that, after the course you are able to use those technologies in your projects. You really go from zero to mastery!

Joel Joseph

Course curriculum

To make sure this course is a good fit for you, you can start learning TensorFlow for free right now by clicking any of the PREVIEW links below.

Introduction

6 lectures

Tensorflow Developer Certificate Zero to Mastery2:52

PREVIEW

Course Outline5:21

PREVIEW

Exercise: Meet Your Classmates and Instructor

START

All Course Resources + Notebooks

START

Python + Machine Learning Monthly

START

How-to's: Speed up videos, Downloading videos, Subtitles

START

Deep Learning and TensorFlow Fundamentals

32 lectures

What is deep learning?4:38

PREVIEW

Why use deep learning?9:38

PREVIEW

What are neural networks?10:26

PREVIEW

What is deep learning already being used for?8:36

PREVIEW

What is and why use TensorFlow?7:56

PREVIEW

What is a Tensor?3:37

PREVIEW

What we're going to cover throughout the course4:29

PREVIEW

How to approach this course5:33

PREVIEW

Need A Refresher?

PREVIEW

Creating your first tensors with TensorFlow and tf.constant()18:45

PREVIEW

Creating tensors with TensorFlow and tf.Variable()7:07

PREVIEW

Creating random tensors with TensorFlow9:40

PREVIEW

Shuffling the order of tensors9:40

PREVIEW

Creating tensors from NumPy arrays11:55

PREVIEW

Getting information from your tensors (tensor attributes)11:57

PREVIEW

Indexing and expanding tensors12:33

PREVIEW

Manipulating tensors with basic operations5:34

PREVIEW

Matrix multiplication with tensors part 111:53

PREVIEW

Matrix multiplication with tensors part 213:29

PREVIEW

Matrix multiplication with tensors part 310:03

PREVIEW

Changing the datatype of tensors6:55

PREVIEW

Tensor aggregation (finding the min, max, mean & more)9:49

PREVIEW

Tensor troubleshooting example (updating tensor datatypes)6:13

PREVIEW

Finding the positional minimum and maximum of a tensor (argmin and argmax)9:31

PREVIEW

Squeezing a tensor (removing all 1-dimension axes)2:59

PREVIEW

One-hot encoding tensors5:46

PREVIEW

Trying out more tensor math operations4:47

PREVIEW

Exploring TensorFlow and NumPy's compatibility5:43

PREVIEW

Making sure our tensor operations run really fast on GPUs10:19

PREVIEW

TensorFlow Fundamentals challenge, exercises & extra-curriculum

PREVIEW

Endorsements On LinkedIn

START

Unlimited Updates

START

Neural network regression with TensorFlow

30 lectures

Introduction to Neural Network Regression with TensorFlow7:33

PREVIEW

Inputs and outputs of a neural network regression model8:59

START

Anatomy and architecture of a neural network regression model7:55

START

Creating sample regression data (so we can model it)12:46

START

Note: Code update for upcoming lecture(s) for TensorFlow 2.7.0+ fix

START

The major steps in modelling with TensorFlow40:30

START

Steps in improving a model with TensorFlow part 16:02

START

Steps in improving a model with TensorFlow part 29:25

START

Steps in improving a model with TensorFlow part 312:33

START

Evaluating a TensorFlow model part 1 ("visualise, visualise, visualise")7:24

START

Evaluating a TensorFlow model part 2 (the three datasets)11:01

START

Evaluating a TensorFlow model part 3 (getting a model summary)17:18

START

Evaluating a TensorFlow model part 4 (visualising a model's layers)7:14

START

Evaluating a TensorFlow model part 5 (visualising a model's predictions)9:16

START

Evaluating a TensorFlow model part 6 (common regression evaluation metrics)8:05

START

Evaluating a TensorFlow regression model part 7 (mean absolute error)5:52

START

Evaluating a TensorFlow regression model part 7 (mean square error)3:18

START

Setting up TensorFlow modelling experiments part 1 (start with a simple model)13:50

START

Setting up TensorFlow modelling experiments part 2 (increasing complexity)11:29

START

Comparing and tracking your TensorFlow modelling experiments10:20

START

How to save a TensorFlow model8:19

START

How to load and use a saved TensorFlow model10:15

START

(Optional) How to save and download files from Google Colab6:18

START

Putting together what we've learned part 1 (preparing a dataset)13:31

START

Putting together what we've learned part 2 (building a regression model)13:20

START

Putting together what we've learned part 3 (improving our regression model)15:47

START

Preprocessing data with feature scaling part 1 (what is feature scaling?)9:34

START

Preprocessing data with feature scaling part 2 (normalising our data)10:57

START

Preprocessing data with feature scaling part 3 (fitting a model on scaled data)7:40

START

TensorFlow Regression challenge, exercises & extra-curriculum

START

Neural network classification in TensorFlow

35 lectures

Introduction to neural network classification in TensorFlow8:25

PREVIEW

Example classification problems (and their inputs and outputs)6:38

START

Input and output tensors of classification problems6:21

START

Typical architecture of neural network classification models with TensorFlow9:36

START

Creating and viewing classification data to model11:34

START

Checking the input and output shapes of our classification data4:38

START

Building a not very good classification model with TensorFlow12:10

START

Trying to improve our not very good classification model9:13

START

Creating a function to view our model's not so good predictions15:08

START

Note: Updates for TensorFlow 2.7.0

START

Make our poor classification model work for a regression dataset24:36

START

Non-linearity part 1: Straight lines and non-straight lines9:38

START

Non-linearity part 2: Building our first neural network with non-linearity5:47

START

Non-linearity part 3: Upgrading our non-linear model with more layers10:18

START

Non-linearity part 4: Modelling our non-linear data once and for all8:37

START

Non-linearity part 5: Replicating non-linear activation functions from scratch14:26

START

Getting great results in less time by tweaking the learning rate14:47

START

Using the TensorFlow History object to plot a model's loss curves6:11

START

Using callbacks to find a model's ideal learning rate17:32

START

Training and evaluating a model with an ideal learning rate9:20

START

Introducing more classification evaluation methods6:04

START

Finding the accuracy of our classification model4:17

START

Creating our first confusion matrix (to see where our model is getting confused)8:27

START

Making our confusion matrix prettier14:00

START

Putting things together with multi-class classification part 1: Getting the data10:37

START

Multi-class classification part 2: Becoming one with the data7:07

START

Multi-class classification part 3: Building a multi-class classification model15:38

START

Multi-class classification part 4: Improving performance with normalisation12:43

START

Multi-class classification part 5: Comparing normalised and non-normalised data4:13

START

Multi-class classification part 6: Finding the ideal learning rate10:38

START

Multi-class classification part 7: Evaluating our model13:16

START

Multi-class classification part 8: Creating a confusion matrix4:26

START

Multi-class classification part 9: Visualising random model predictions10:42

START

What "patterns" is our model learning?15:33

START

TensorFlow classification challenge, exercises & extra-curriculum

START

Computer Vision and Convolutional Neural Networks in TensorFlow

37 lectures

Introduction to Computer Vision with TensorFlow9:36

START

Introduction to Convolutional Neural Networks (CNNs) with TensorFlow7:59

START

Downloading an image dataset for our first Food Vision model8:27

START

Becoming One With Data5:05

START

Becoming One With Data Part 212:26

START

Becoming One With Data Part 34:22

START

Building an end to end CNN Model18:17

START

Using a GPU to run our CNN model 5x faster9:17

START

Trying a non-CNN model on our image data8:51

START

Improving our non-CNN model by adding more layers9:52

START

Breaking our CNN model down part 1: Becoming one with the data9:03

START

Breaking our CNN model down part 2: Preparing to load our data11:46

START

Breaking our CNN model down part 3: Loading our data with ImageDataGenerator9:54

START

Breaking our CNN model down part 4: Building a baseline CNN model8:02

START

Breaking our CNN model down part 5: Looking inside a Conv2D layer15:20

START

Breaking our CNN model down part 6: Compiling and fitting our baseline CNN7:14

START

Breaking our CNN model down part 7: Evaluating our CNN's training curves11:45

START

Breaking our CNN model down part 8: Reducing overfitting with Max Pooling13:40

START

Breaking our CNN model down part 9: Reducing overfitting with data augmentation6:52

START

Breaking our CNN model down part 10: Visualizing our augmented data15:04

START

Breaking our CNN model down part 11: Training a CNN model on augmented data8:49

START

Breaking our CNN model down part 12: Discovering the power of shuffling data10:01

START

Breaking our CNN model down part 13: Exploring options to improve our model5:21

START

Downloading a custom image to make predictions on4:54

START

Writing a helper function to load and preprocessing custom images10:00

START

Making a prediction on a custom image with our trained CNN10:08

START

Multi-class CNN's part 1: Becoming one with the data14:59

START

Multi-class CNN's part 2: Preparing our data (turning it into tensors)6:38

START

Multi-class CNN's part 3: Building a multi-class CNN model7:24

START

Multi-class CNN's part 4: Fitting a multi-class CNN model to the data6:02

START

Multi-class CNN's part 5: Evaluating our multi-class CNN model4:51

START

Multi-class CNN's part 6: Trying to fix overfitting by removing layers12:19

START

Multi-class CNN's part 7: Trying to fix overfitting with data augmentation11:45

START

Multi-class CNN's part 8: Things you could do to improve your CNN model4:23

START

Multi-class CNN's part 9: Making predictions with our model on custom images9:22

START

Saving and loading our trained CNN model6:21

START

TensorFlow computer vision and CNNs challenge, exercises & extra-curriculum

START

Transfer Learning in TensorFlow Part 1: Feature extraction

11 lectures

What is and why use transfer learning?10:12

START

Downloading and preparing data for our first transfer learning model14:39

START

Introducing Callbacks in TensorFlow and making a callback to track our models10:01

START

Exploring the TensorFlow Hub website for pretrained models9:51

START

Building and compiling a TensorFlow Hub feature extraction model14:00

START

Blowing our previous models out of the water with transfer learning9:13

START

Plotting the loss curves of our ResNet feature extraction model7:35

START

Building and training a pre-trained EfficientNet model on our data9:42

START

Different Types of Transfer Learning11:40

START

Comparing Our Model's Results15:16

START

TensorFlow Transfer Learning Part 1 challenge, exercises & extra-curriculum

START

Transfer Learning in TensorFlow Part 2: Fine tuning

28 lectures

Introduction to Transfer Learning in TensorFlow Part 2: Fine-tuning6:16

START

Importing a script full of helper functions (and saving lots of space)7:35

START

Exercise: Imposter Syndrome2:55

START

Downloading and turning our images into a TensorFlow BatchDataset15:38

START

Discussing the four (actually five) modelling experiments we're running2:15

START

Comparing the TensorFlow Keras Sequential API versus the Functional API2:34

START

Creating our first model with the TensorFlow Keras Functional API11:38

START

Compiling and fitting our first Functional API model10:53

START

Getting a feature vector from our trained model13:39

START

Drilling into the concept of a feature vector (a learned representation)3:43

START

Downloading and preparing the data for Model 1 (1 percent of training data)9:51

START

Building a data augmentation layer to use inside our model12:06

START

Note: Small fix for next video, for images not augmenting

START

Visualizing what happens when images pass through our data augmentation layer21:50

START

Building Model 1 (with a data augmentation layer and 1% of training data)15:55

START

Building Model 2 (with a data augmentation layer and 10% of training data)16:37

START

Creating a ModelCheckpoint to save our model's weights during training7:25

START

Fitting and evaluating Model 2 (and saving its weights using ModelCheckpoint)7:14

START

Loading and comparing saved weights to our existing trained Model 27:17

START

Preparing Model 3 (our first fine-tuned model)20:26

START

Fitting and evaluating Model 3 (our first fine-tuned model)7:45

START

Comparing our model's results before and after fine-tuning10:26

START

Downloading and preparing data for our biggest experiment yet (Model 4)6:24

START

Preparing our final modelling experiment (Model 4)12:00

START

Fine-tuning Model 4 on 100% of the training data and evaluating its results10:19

START

Comparing our modelling experiment results in TensorBoard10:46

START

How to view and delete previous TensorBoard experiments2:04

START

Transfer Learning in TensorFlow Part 2 challenge, exercises and extra-curriculum

START

Transfer Learning with TensorFlow Part 3: Scaling Up

23 lectures

Introduction to Transfer Learning Part 3: Scaling Up6:19

START

Getting helper functions ready and downloading data to model13:34

START

Outlining the model we're going to build and building a ModelCheckpoint callback5:38

START

Creating a data augmentation layer to use with our model4:39

START

Creating a headless EfficientNetB0 model with data augmentation built in8:58

START

Fitting and evaluating our biggest transfer learning model yet7:56

START

Unfreezing some layers in our base model to prepare for fine-tuning11:28

START

Fine-tuning our feature extraction model and evaluating its performance8:23

START

Saving and loading our trained model6:25

START

Downloading a pretrained model to make and evaluate predictions with6:34

START

Making predictions with our trained model on 25,250 test samples12:46

START

Unravelling our test dataset for comparing ground truth labels to predictions6:05

START

Confirming our model's predictions are in the same order as the test labels5:17

START

Creating a confusion matrix for our model's 101 different classes12:07

START

Evaluating every individual class in our dataset14:16

START

Plotting our model's F1-scores for each separate class7:36

START

Creating a function to load and prepare images for making predictions12:08

START

Making predictions on our test images and evaluating them16:06

START

Discussing the benefits of finding your model's most wrong predictions6:09

START

Writing code to uncover our model's most wrong predictions11:16

START

Plotting and visualizing the samples our model got most wrong10:36

START

Making predictions on and plotting our own custom images9:49

START

Transfer Learning in TensorFlow Part 3 challenge, exercises and extra-curriculum

START

Milestone Project 1: Food Vision Big™

16 lectures

Introduction to Milestone Project 1: Food Vision Big™5:44

START

Making sure we have access to the right GPU for mixed precision training10:17

START

Getting helper functions ready3:06

START

Introduction to TensorFlow Datasets (TFDS)12:03

START

Exploring and becoming one with the data (Food101 from TensorFlow Datasets)15:56

START

Creating a preprocessing function to prepare our data for modelling15:50

START

Batching and preparing our datasets (to make them run fast)13:47

START

Exploring what happens when we batch and prefetch our data6:49

START

Creating modelling callbacks for our feature extraction model7:14

START

Note: Mixed Precision producing errors for TensorFlow 2.5+

START

Turning on mixed precision training with TensorFlow10:05

START

Creating a feature extraction model capable of using mixed precision training12:42

START

Checking to see if our model is using mixed precision training layer by layer7:56

START

Training and evaluating a feature extraction model (Food Vision Big™)10:19

START

Introducing your Milestone Project 1 challenge: build a model to beat DeepFood7:47

START

Milestone Project 1: Food Vision Big™, exercises and extra-curriculum

START

NLP Fundamentals in TensorFlow

35 lectures

Welcome to natural language processing with TensorFlow!

START

Introduction to Natural Language Processing (NLP) and Sequence Problems12:51

START

Example NLP inputs and outputs7:22

START

The typical architecture of a Recurrent Neural Network (RNN)9:03

START

Preparing a notebook for our first NLP with TensorFlow project8:52

START

Becoming one with the data and visualizing a text dataset16:41

START

Splitting data into training and validation sets6:26

START

Converting text data to numbers using tokenisation and embeddings (overview)9:22

START

Setting up a TensorFlow TextVectorization layer to convert text to numbers17:10

START

Mapping the TextVectorization layer to text data and turning it into numbers11:02

START

Creating an Embedding layer to turn tokenised text into embedding vectors12:27

START

Discussing the various modelling experiments we're going to run8:57

START

Model 0: Building a baseline model to try and improve upon9:25

START

Creating a function to track and evaluate our model's results12:14

START

Model 1: Building, fitting and evaluating our first deep model on text data20:51

START

Visualizing our model's learned word embeddings with TensorFlow's projector tool20:43

START

High-level overview of Recurrent Neural Networks (RNNs) + where to learn more9:34

START

Model 2: Building, fitting and evaluating our first TensorFlow RNN model (LSTM)18:16

START

Model 3: Building, fitting and evaluating a GRU-cell powered RNN16:56

START

Model 4: Building, fitting and evaluating a bidirectional RNN model19:34

START

Discussing the intuition behind Conv1D neural networks for text and sequences19:31

START

Model 5: Building, fitting and evaluating a 1D CNN for text9:57

START

Using TensorFlow Hub for pretrained word embeddings (transfer learning for NLP)13:45

START

Model 6: Building, training and evaluating a transfer learning model for NLP10:45

START

Preparing subsets of data for model 7 (same as model 6 but 10% of data)10:52

START

Model 7: Building, training and evaluating a transfer learning model on 10% data10:04

START

Fixing our data leakage issue with model 7 and retraining it13:42

START

Comparing all our modelling experiments evaluation metrics13:14

START

Uploading our model's training logs to TensorBoard and comparing them11:14

START

Saving and loading in a trained NLP model with TensorFlow10:25

START

Downloading a pretrained model and preparing data to investigate predictions13:24

START

Visualizing our model's most wrong predictions8:28

START

Making and visualizing predictions on the test dataset8:27

START

Understanding the concept of the speed/score tradeoff15:01

START

NLP Fundamentals in TensorFlow challenge, exercises and extra-curriculum

START

Milestone Project 2: SkimLit

36 lectures

Introduction to Milestone Project 2: SkimLit14:20

START

What we're going to cover in Milestone Project 2 (NLP for medical abstracts)7:22

START

SkimLit inputs and outputs11:02

START

Setting up our notebook for Milestone Project 2 (getting the data)14:58

START

Visualizing examples from the dataset (becoming one with the data)13:18

START

Writing a preprocessing function to structure our data for modelling19:50

START

Performing visual data analysis on our preprocessed text7:55

START

Turning our target labels into numbers (ML models require numbers)13:15

START

Model 0: Creating, fitting and evaluating a baseline model for SkimLit9:25

START

Preparing our data for deep sequence models9:55

START

Creating a text vectoriser to map our tokens (text) to numbers14:07

START

Creating a custom token embedding layer with TensorFlow9:14

START

Creating fast loading dataset with the TensorFlow tf.data API9:49

START

Model 1: Building, fitting and evaluating a Conv1D with token embeddings17:21

START

Preparing a pretrained embedding layer from TensorFlow Hub for Model 210:53

START

Model 2: Building, fitting and evaluating a Conv1D model with token embeddings11:30

START

Creating a character-level tokeniser with TensorFlow's TextVectorization layer23:24

START

Creating a character-level embedding layer with tf.keras.layers.Embedding7:44

START

Model 3: Building, fitting and evaluating a Conv1D model on character embeddings13:45

START

Discussing how we're going to build Model 4 (character + token embeddings)6:04

START

Model 4: Building a multi-input model (hybrid token + character embeddings)15:36

START

Model 4: Plotting and visually exploring different data inputs7:32

START

Crafting multi-input fast loading tf.data datasets for Model 48:41

START

Model 4: Building, fitting and evaluating a hybrid embedding model13:18

START

Model 5: Adding positional embeddings via feature engineering (overview)7:18

START

Encoding the line number feature to used with Model 512:25

START

Encoding the total lines feature to be used with Model 57:56

START

Model 5: Building the foundations of a tribrid embedding model9:19

START

Model 5: Completing the build of a tribrid embedding model for sequences14:08

START

Visually inspecting the architecture of our tribrid embedding model10:25

START

Creating multi-level data input pipelines for Model 5 with the tf.data API9:00

START

Bringing SkimLit to life!!! (fitting and evaluating Model 5)10:35

START

Comparing the performance of all of our modelling experiments9:36

START

Saving, loading & testing our best performing model7:48

START

Congratulations and your challenge before heading to the next module12:33

START

Milestone Project 2 (SkimLit) challenge, exercises and extra-curriculum

START

Time Series fundamentals in TensorFlow + Milestone Project 3: BitPredict

64 lectures

Welcome to time series fundamentals with TensorFlow + Milestone Project 3!

START

Introduction to Milestone Project 3 (BitPredict) & where you can get help3:53

START

What is a time series problem and example forecasting problems at Uber7:45

START

Example forecasting problems in daily life4:52

START

What can be forecast?7:57

START

What we're going to cover (broadly)2:35

START

Time series forecasting inputs and outputs8:55

START

Downloading and inspecting our Bitcoin historical dataset14:58

START

Different kinds of time series patterns & different amounts of feature variables7:39

START

Visualizing our Bitcoin historical data with pandas4:52

START

Reading in our Bitcoin data with Python's CSV module10:58

START

Creating train and test splits for time series (the wrong way)8:37

START

Creating train and test splits for time series (the right way)7:12

START

Creating a plotting function to visualize our time series data7:57

START

Discussing the various modelling experiments were going to be running9:11

START

Model 0: Making and visualizing a naive forecast model12:16

START

Discussing some of the most common time series evaluation metrics11:11

START

Implementing MASE with TensorFlow9:38

START

Creating a function to evaluate our model's forecasts with various metrics10:11

START

Discussing other non-TensorFlow kinds of time series forecasting models5:06

START

Formatting data Part 2: Creating a function to label our windowed time series13:01

START

Discussing the use of windows and horizons in time series data7:50

START

Writing a preprocessing function to turn time series data into windows & labels23:35

START

Turning our windowed time series data into training and test sets10:01

START

Creating a modelling checkpoint callback to save our best performing model7:25

START

Model 1: Building, compiling and fitting a deep learning model on Bitcoin data16:58

START

Creating a function to make predictions with our trained models14:02

START

Model 2: Building, fitting and evaluating a deep model with a larger window size-2717:43

START

Model 3: Building, fitting and evaluating a model with a larger horizon size13:15

START

Adjusting the evaluation function to work for predictions with larger horizons8:34

START

Model 3: Visualizing the results8:44

START

Comparing our modelling experiments so far and discussing autocorrelation9:44

START

Preparing data for building a Conv1D model13:21

START

Model 4: Building, fitting and evaluating a Conv1D model on our Bitcoin data14:51

START

Model 5: Building, fitting and evaluating a LSTM (RNN) model on our Bitcoin data16:05

START

Investigating how to turn our univariate time series into multivariate13:52

START

Creating and plotting a multivariate time series with BTC price and block reward12:12

START

Preparing our multivariate time series for a model13:37

START

Model 6: Building, fitting and evaluating a multivariate time series model9:25

START

Model 7: Discussing what we're going to be doing with the N-BEATS algorithm9:39

START

Model 7: Replicating the N-BEATS basic block with TensorFlow layer subclassing18:38

START

Model 7: Testing our N-BEATS block implementation with dummy data inputs15:02

START

Model 7: Creating a performant data pipeline for the N-BEATS model with tf.data14:09

START

Model 7: Setting up hyperparameters for the N-BEATS algorithm8:50

START

Model 7: Getting ready for residual connections12:55

START

Model 7: Outlining the steps we're going to take to build the N-BEATS model10:05

START

Model 7: Putting together the pieces of the puzzle of the N-BEATS model22:22

START

Model 7: Plotting the N-BEATS algorithm we've created and admiring its beauty6:46

START

Model 8: Ensemble model overview4:43

START

Model 8: Building, compiling and fitting an ensemble of models20:04

START

Model 8: Making and evaluating predictions with our ensemble model16:09

START

Discussing the importance of prediction intervals in forecasting12:56

START

Getting the upper and lower bounds of our prediction intervals7:57

START

Plotting the prediction intervals of our ensemble model predictions13:02

START

(Optional) Discussing the types of uncertainty in machine learning13:41

START

Model 9: Preparing data to create a model capable of predicting into the future8:24

START

Model 9: Building, compiling and fitting a future predictions model5:01

START

Model 9: Discussing what's required for our model to make future predictions8:30

START

Model 9: Creating a function to make forecasts into the future12:08

START

Model 9: Plotting our model's future forecasts13:09

START

Model 10: Introducing the turkey problem and making data for it14:15

START

Model 10: Building a model to predict on turkey data (why forecasting is BS)13:38

START

Comparing the results of all of our models and discussing where to go next12:59

START

TensorFlow Time Series Fundamentals Challenge and Extra Resources

START

Passing the TensorFlow Developer Certificate Exam

6 lectures

Get ready to be TensorFlow Developer Certified!

START

What is the TensorFlow Developer Certification?5:28

START

Why the TensorFlow Developer Certification?6:57

START

How to prepare (your brain) for the TensorFlow Developer Certification8:14

START

How to prepare (your computer) for the TensorFlow Developer Certification12:43

START

What to do after the TensorFlow Developer Certification exam2:13

START

Where To Go From Here?

6 lectures

Thank You!1:17

START

Review This Course!

START

Become An Alumni

START

LinkedIn Endorsements

START

TensorFlow Certificate

START

Learning Guideline

START

Appendix: Machine Learning Primer

10 lectures

Quick Note: Upcoming Videos

START

What is Machine Learning?6:52

START

AI/Machine Learning/Data Science4:51

START

Exercise: Machine Learning Playground6:16

START

How Did We Get Here?6:03

START

Exercise: YouTube Recommendation Engine4:24

START

Types of Machine Learning4:41

START

Are You Getting It Yet?

START

What Is Machine Learning? Round 24:44

START

Section Review1:48

START

Appendix: Machine Learning and Data Science Framework

16 lectures

Quick Note: Upcoming Videos

START

Section Overview3:08

START

Introducing Our Framework2:38

START

6 Step Machine Learning Framework4:59

START

Types of Machine Learning Problems10:32

START

Types of Data4:50

START

Types of Evaluation3:31

START

Features In Data5:22

START

Modelling - Splitting Data5:58

START

Modelling - Picking the Model4:35

START

Modelling - Tuning3:17

START

Modelling - Comparison9:32

START

Overfitting and Underfitting Definitions

START

Experimentation3:35

START

Tools We Will Use3:59

START

Optional: Elements of AI(document)

START

Appendix: Pandas for Data Analysis

14 lectures

Quick Note: Upcoming Videos

START

Section Overview2:27

START

Downloading Workbooks and Assignments

START

Pandas Introduction4:29

START

Series, Data Frames and CSVs13:21

START

Data from URLs

START

Describing Data with Pandas9:48

START

Selecting and Viewing Data with Pandas11:08

START

Selecting and Viewing Data with Pandas Part 213:06

START

Manipulating Data13:56

START

Manipulating Data 29:56

START

Manipulating Data 310:12

START

Assignment: Pandas Practice

START

How To Download The Course Assignments7:43

START

Appendix: NumPy

19 lectures

Quick Note: Upcoming Videos

START

Section Overview2:40

START

NumPy Introduction5:17

START

Quick Note: Correction In Next Video

START

NumPy DataTypes and Attributes14:05

START

Creating NumPy Arrays9:22

START

NumPy Random Seed7:17

START

Viewing Arrays and Matrices9:35

START

Manipulating Arrays11:31

START

Manipulating Arrays 29:44

START

Standard Deviation and Variance7:10

START

Reshape and Transpose7:26

START

Dot Product vs Element Wise11:45

START

Exercise: Nut Butter Store Sales13:04

START

Comparison Operators3:33

START

Sorting Arrays6:19

START

Turn Images Into NumPy Arrays7:37

START

Assignment: NumPy Practice

START

Optional: Extra NumPy resources

START

Meet your instructor

Your TensorFlow instructor (Daniel) isn't just an expert with years of real-world professional experience. He has been in your shoes. He makes learning fun. He makes complex topics feel simple. He will motivate you. He will push you. And he will go above and beyond to help you succeed.

Daniel Bourke

Hi, I'm Daniel Bourke!

Daniel, a self-taught Machine Learning Engineer, has worked at one of Australia's fastest-growing artificial intelligence agencies, Max Kelsen, and is now using his expertise to teach thousands of students data science and machine learning.

SEE MY BIO & COURSES

Daniel Bourke

Machine Learning Engineer

Frequently asked questions

Are there any prerequisites for this course?

  • No previous TensorFlow knowledge required. Basic understanding of Machine Learning is helpful but if you've taken Daniel's Machine Learning course, you're all set!
  • A computer (Linux/Windows/Mac) with an internet connection

Who is this course for?

  • You want a step-by-step guide to pass the TensorFlow Developer Certificate exam so that you can join Google's Certificate Network and get hired at a top company, making over $100,000 / year
  • You want to be recognized as a top tier quality candidate by recruiters at leading companies
  • Anyone who wants to learn TensorFlow and how to pass the TensorFlow exam from an industry expert (Daniel Bourke) who has taken and passed the exam and has actually worked in the field
  • Students, developers, and data scientists who want to demonstrate practical machine learning skills by actually building and training real models using TensorFlow
  • Anyone looking to expand their knowledge when it comes to AI, Machine Learning and Deep Learning
  • Anyone looking to get real-world experience building TensorFlow models using Computer Vision, Convolutional Neural Networks and Natural Language Processing with the latest version of TensorFlow

Do you provide a certificate of completion?

We definitely do and they are quite nice. You will also be able to add Zero To Mastery Academy to the education section of your LinkedIn profile as well.

Can I use the course projects in my portfolio?

Yes, you’d be crazy not to in our slightly biased opinion! All projects are downloadable and ready to use the minute you join.

Many of our students tell us the projects they built while following along with our courses were what got them interviews and because they built the projects themselves, they could confidently explain and walk through their work during the interview.

You know what that means? Job offer!

Can I download the videos?

Definitely. You can download any and all lessons for personal use. We do everything we can to make learning easy, fun and accessible. Whether that’s on your commute, on a flight or just when you have limited access to good WiFi.

Can I learn TensorFlow and pass the exam with free resources?

Daniel here... Yes, of course you can. You can go learn all the skills you need by going through the TensorFlow documentation.

In fact, when I need to practice something, I copy the documentation examples verbatim (every line of code), practice understanding it line by line, then see if I can do it myself.

However, that will likely take you a long time. This course puts you on a fast track to passing the TensorFlow exam by providing you with a clear step-by-step guide with absolutely everything you need to learn in one place.

Still have more questions about the Academy?

Still have more questions specific to the Academy membership? No problem, we answer some more here.

Take the next step and invest in a better you

Choose your currency:
$ USD US Dollar
Monthly
100% OFF$39 / month
$39 / month
You're ready to upskill and advance your career
Start Learning Now
Save 40% vs. monthly (that's $189 a year)
Annual
100% OFF$279 / year
$279 / year
$23 / month
You're committed to getting hired and starting a career in tech
Start Learning Now
Lifetime
100% OFF$999
$999
Only pay once, ever
You're serious about advancing your career and never getting left behind
Start Learning Now

Every ZTM membership includes:

Unlimited access to all courses, workshops, and career paths
Invite to private Discord with 400,000+ members
Access to private Linkedin networking group
Custom ZTM course completion certificates
Download all lessons for offline learning
Unlimited, priority access to all future courses, content, and features
100% RISK FREE

We know you'll love ZTM. That's why we provide a no hassle, 30-day money back guarantee.