on-demand course

TensorFlow for Deep Learning Bootcamp: Zero to Mastery

with Zero To Mastery Inc., Daniel Bourke

July 2026

Intermediate

62h 23m

English

Packt Publishing

Closed Captioning available in English

Watch now

Unlock full access

Includes

Badge

Course outline

TensorFlow for Deep Learning: Zero to Mastery
1m 38s
Course Outline
4m 17s
What is deep learning?
4m 38s
Why use deep learning?
9m 39s
What are neural networks?
10m 26s
What is deep learning already being used for?
8m 37s
What is and why use TensorFlow?
7m 56s
What is a Tensor?
3m 38s
What we're going to cover throughout the course
4m 29s
How to approach this course
5m 34s
Creating your first tensors with TensorFlow and tf.constant()
18m 45s
Creating tensors with TensorFlow and tf.Variable()
7m 8s
Creating random tensors with TensorFlow
9m 40s
Shuffling the order of tensors
9m 41s
Creating tensors from NumPy arrays
11m 55s
Getting information from your tensors (tensor attributes)
11m 57s
Indexing and expanding tensors
12m 33s
Manipulating tensors with basic operations
5m 35s
Matrix multiplication with tensors part 1
11m 54s
Matrix multiplication with tensors part 2
13m 30s
Matrix multiplication with tensors part 3
10m 3s
Changing the datatype of tensors
6m 56s
Tensor aggregation (finding the min, max, mean and more)
9m 49s
Tensor troubleshooting example (updating tensor datatypes)
6m 14s
Finding the positional minimum and maximum of a tensor (argmin and argmax)
9m 31s
Squeezing a tensor (removing all 1-dimension axes)
3m 0s
One-hot encoding tensors
5m 46s
Trying out more tensor math operations
4m 48s
Exploring TensorFlow and NumPy's compatibility
5m 43s
Making sure our tensor operations run really fast on Graphics Processing Units
10m 20s
Introduction to Neural Network Regression with TensorFlow
7m 33s
Inputs and outputs of a neural network regression model
8m 59s
Anatomy and architecture of a neural network regression model
7m 55s
Creating sample regression data (so we can model it)
12m 47s
The major steps in modelling with TensorFlow
20m 16s
Steps in improving a model with TensorFlow part 1
6m 3s
Steps in improving a model with TensorFlow part 2
9m 26s
Steps in improving a model with TensorFlow part 3
12m 33s
Evaluating a TensorFlow model part 1 ("visualise, visualise, visualise")
7m 24s
Evaluating a TensorFlow model part 2 (the three datasets)
11m 2s
Evaluating a TensorFlow model part 3 (getting a model summary)
17m 18s
Evaluating a TensorFlow model part 4 (visualising a model's layers)
7m 15s
Evaluating a TensorFlow model part 5 (visualising a model's predictions)
9m 17s
Evaluating a TensorFlow model part 6 (common regression evaluation metrics)
8m 6s
Evaluating a TensorFlow regression model part 7 (mean absolute error)
5m 53s
Evaluating a TensorFlow regression model part 7 (mean square error)
3m 19s
Setting up TensorFlow modelling experiments part 1 (start with a simple model)
13m 50s
Setting up TensorFlow modelling experiments part 2 (increasing complexity)
11m 30s
Comparing and tracking your TensorFlow modelling experiments
10m 20s
How to save a TensorFlow model
8m 20s
How to load and use a saved TensorFlow model
10m 16s
(Optional) How to save and download files from Google Colab
6m 19s
Putting together what we've learned part 1 (preparing a dataset)
13m 31s
Putting together what we've learned part 2 (building a regression model)
13m 21s
Putting together what we've learned part 3 (improving our regression model)
15m 47s
Preprocessing data with feature scaling part 1 (what is feature scaling?)
9m 34s
Preprocessing data with feature scaling part 2 (normalising our data)
10m 57s
Preprocessing data with feature scaling part 3 (fitting a model on scaled data)
7m 41s
Introduction to Neural Network Classification with TensorFlow
8m 25s
Example classification problems
6m 38s
Input and output tensors of classification problems
6m 22s
Typical architecture of neural network classification models
9m 36s
Creating and viewing classification data to model
11m 34s
Checking the input and output shapes of our classification data
4m 38s
Building a not very good classification model
12m 11s
Trying to improve our not very good classification model
9m 13s
Creating a function to view our model's not so good predictions
15m 9s
Making our poor classification model work for a regression dataset
12m 19s
Non-linearity part 1: Straight lines and non-straight lines
9m 39s
Non-linearity part 2: Building our first neural network with non-linearity
5m 48s
Non-linearity part 3: Upgrading our non-linear model with more layers
10m 19s
Non-linearity part 4: Modelling our non-linear data once again
8m 38s
Non-linearity part 5: Replicating non-linear activation functions
14m 27s
Getting great results in less time by tweaking the learning rate
14m 48s
Using the TensorFlow History object to plot a model's loss curves
6m 12s
Using callbacks to find a model's ideal learning rate
17m 32s
Training and evaluating a model with an ideal learning rate
9m 21s
Introducing more classification evaluation methods
6m 5s
Finding the accuracy of our classification model
4m 18s
Creating our first confusion matrix
8m 28s
Making our confusion matrix prettier
14m 1s
Putting things together with multiclass classification part 1: Introduction
10m 38s
Multiclass classification part 2: Becoming one with the data
7m 8s
Multiclass classification part 3: Building a multiclass classification model
15m 38s
Multiclass classification part 4: Improving performance with normalisation
12m 43s
Multiclass classification part 5: Comparing normalised and non-normalised data
4m 14s
Multiclass classification part 6: Finding the ideal learning rate
10m 39s
Multiclass classification part 7: Evaluating our model
13m 17s
Multiclass classification part 8: Creating a confusion matrix
4m 26s
Multiclass classification part 9: Visualising random model predictions
10m 42s
What patterns is our model learning?
15m 33s
Introduction to Computer Vision
9m 36s
Introduction to Convolutional Neural Networks
8m 0s
Downloading image data for our first Food Vision model
8m 27s
Becoming one with the data
5m 5s
Becoming one with the data part 2
12m 26s
Becoming one with the data part 3
4m 23s
Building an end-to-end Convolutional Neural Network model
18m 18s
Using a Graphics Processing Unit to run our Convolutional Neural Network model five times faster
9m 17s
Trying a non-Convolutional Neural Network model on our image data
8m 51s
Improving our non-Convolutional Neural Network model by adding more layers
9m 52s
Convolutional Neural Network breakdown part 1: Becoming one with the data
9m 3s
Convolutional Neural Network breakdown part 2: Preparing to load our data
11m 46s
Convolutional Neural Network breakdown part 3: Loading our data with ImageDataGenerator
9m 55s
Convolutional Neural Network breakdown part 4: Building a baseline Convolutional Neural Network model
8m 3s
Convolutional Neural Network breakdown part 5: Looking inside a Conv2D layer
15m 21s
Convolutional Neural Network breakdown part 6: Compiling and fitting our baseline Convolutional Neural Network
7m 14s
Convolutional Neural Network breakdown part 7: Evaluating our Convolutional Neural Network training curves
11m 46s
Convolutional Neural Network breakdown part 8: Reducing overfitting with max pooling
13m 40s
Convolutional Neural Network breakdown part 9: Reducing overfitting with data augmentation
6m 52s
Convolutional Neural Network breakdown part 10: Visualising our augmented data
15m 4s
Convolutional Neural Network breakdown part 11: Training a Convolutional Neural Network model on augmented data
8m 49s
Convolutional Neural Network breakdown part 12: Discovering the power of shuffling data
10m 2s
Convolutional Neural Network breakdown part 13: Exploring options to improve our model
5m 22s
Downloading a custom image to make predictions on
4m 54s
Writing a helper function to load and preprocess custom images
10m 1s
Making a prediction on a custom image with our trained Convolutional Neural Network
10m 9s
Multiclass Convolutional Neural Networks part 1: Becoming one with the data
15m 0s
Multiclass Convolutional Neural Networks part 2: Preparing our data
6m 38s
Multiclass Convolutional Neural Networks part 3: Building a multiclass Convolutional Neural Network model
7m 25s
Multiclass Convolutional Neural Networks part 4: Fitting a multiclass Convolutional Neural Network model to the data
6m 3s
Multiclass Convolutional Neural Networks part 5: Evaluating our multiclass Convolutional Neural Network model
4m 51s
Multiclass Convolutional Neural Networks part 6: Trying to fix overfitting by simplifying our model
12m 20s
Multiclass Convolutional Neural Networks part 7: Trying to fix overfitting with data augmentation
11m 46s
Multiclass Convolutional Neural Networks part 8: Things you could do to improve the model
4m 24s
Multiclass Convolutional Neural Networks part 9: Predicting with our model on custom images
9m 22s
Saving and loading our trained Convolutional Neural Network model
6m 21s
What is transfer learning and why use it?
10m 12s
Preparing data for our first transfer learning model
14m 40s
Introducing callbacks in TensorFlow and making a callback to track modelling experiments
10m 1s
Exploring the TensorFlow Hub website for pretrained models
9m 51s
Building and compiling a TensorFlow Hub feature extraction model
14m 0s
Blowing our previous models out of the water with transfer learning
9m 14s
Plotting the loss curves of our ResNet feature extraction model
7m 36s
Building and training a pretrained EfficientNet model on our data
9m 42s
Different types of transfer learning
11m 40s
Comparing our model's results
15m 17s
Introduction to Transfer Learning in TensorFlow Part 2: Fine-tuning
6m 16s
Importing a script full of helper functions
7m 35s
Exercise: Imposter Syndrome
2m 56s
Downloading and turning our images into a TensorFlow BatchDataset
15m 39s
Discussing the four modelling experiments we are going to run
2m 15s
Comparing the TensorFlow Keras Sequential API versus the Functional API
2m 34s
Creating our first model with the TensorFlow Keras Functional API
11m 39s
Compiling and fitting our first Functional API model
10m 54s
Getting a feature vector from our trained model
13m 39s
Drilling into the concept of a feature vector
3m 43s
Preparing the data for model 1
9m 52s
Building a data augmentation layer to use inside our model
12m 6s
Visualising what happens when images pass through our data augmentation layer
10m 56s
Building model 1
15m 55s
Building model 2
16m 37s
Creating ModelCheckpoint to save our model's weights during training
7m 25s
Fitting and evaluating model 2
7m 14s
Loading and comparing saved weights to our existing model
7m 18s
Preparing model 3
20m 27s
Fitting and evaluating model 3
7m 46s
Comparing our model's results before and after fine-tuning
10m 27s
Preparing data for our biggest experiment yet, model 4
6m 25s
Preparing our final modelling experiment, model 4
12m 0s
Fine-tuning model 4 on 100 percent of the training data
10m 19s
Comparing our modelling experiment results in TensorBoard
10m 46s
How to view and delete previous TensorBoard experiments
2m 4s
Introduction to Transfer Learning Part 3: Scaling Up
6m 20s
Getting helper functions ready and downloading data to model
13m 34s
Outlining the model we are going to build and building a feature extraction model
5m 39s
Creating a data augmentation layer to use with our model
4m 40s
Creating a headless EfficientNetB0 model with data augmentation
8m 59s
Fitting and evaluating our biggest transfer learning model yet
7m 57s
Unfreezing some layers in our base model to prepare for fine-tuning
11m 28s
Fine-tuning our feature extraction model and evaluating the results
8m 24s
Saving and loading our trained model
6m 26s
Downloading a pretrained model to make and evaluate predictions
6m 34s
Predicting with our trained model on 25,250 test samples
12m 47s
Unravelling our test data for comparing ground truth labels and predictions
6m 5s
Confirming our model's predictions are in the same order as our test labels
5m 17s
Creating a confusion matrix for our model's 101 different classes
12m 8s
Evaluating every individual class in our data
14m 16s
Plotting our model's F1-scores for each separate class
7m 36s
Creating a function to load and prepare images for prediction
12m 9s
Predicting on our test images and evaluating them
16m 6s
Discussing the benefits of finding your model's most wrong predictions
6m 9s
Writing code to uncover our model's most wrong predictions
11m 16s
Plotting and visualising the samples our model got most wrong
10m 36s
Predicting on and plotting our own custom images
9m 50s
Introduction to Milestone Project 1: Food Vision Big™
5m 44s
Making sure we have access to the right Graphics Processing Unit for mixed precision training
10m 18s
Getting helper functions ready
3m 6s
Introduction to TensorFlow Datasets
12m 3s
Exploring and becoming one with the data (Food101 from TensorFlow Datasets)
15m 56s
Creating a preprocessing function to prepare our data for modelling
15m 50s
Batching and preparing our datasets to make them run fast
13m 48s
Exploring what happens when we batch and prefetch our data
6m 49s
Creating modelling callbacks for our feature extraction model
7m 14s
Turning on mixed precision training with TensorFlow
10m 5s
Creating a feature extraction model capable of using mixed precision training
12m 43s
Checking to see if our model is using mixed precision training layer by layer
7m 57s
Training and evaluating a feature extraction model (Food Vision Big™)
10m 19s
Introducing your Milestone Project 1 challenge: build a model to beat DeepFood
7m 48s
Introduction to Natural Language Processing and sequence problems
12m 52s
Example Natural Language Processing inputs and outputs
7m 23s
The typical architecture of a Recurrent Neural Network
9m 3s
Preparing a notebook for our first Natural Language Processing with TensorFlow project
8m 53s
Becoming one with the data and visualizing a text dataset
16m 41s
Splitting data into training and validation sets
6m 27s
Converting text data to numbers using tokenisation and embeddings
9m 23s
Setting up a TensorFlow TextVectorization layer to convert text to numbers
17m 10s
Mapping the TextVectorization layer to text data and turning it into numbers
11m 3s
Creating an Embedding layer to turn tokenised text into embedding vectors
12m 27s
Discussing the various modelling experiments we are going to run
8m 58s
Model 0: Building a baseline model to try and improve upon
9m 25s
Creating a function to track and evaluate our model's results
12m 14s
Model 1: Building, fitting and evaluating our first deep model on text data
20m 52s
Visualizing our model's learned word embeddings with TensorFlow's projector tool
20m 44s
High-level overview of Recurrent Neural Networks and where to learn more
9m 34s
Model 2: Building, fitting and evaluating our first TensorFlow Recurrent Neural Network model with Long Short-Term Memory
18m 17s
Model 3: Building, fitting and evaluating a Gated Recurrent Unit-cell powered Recurrent Neural Network
16m 56s
Model 4: Building, fitting and evaluating a bidirectional Recurrent Neural Network model
19m 35s
Discussing the intuition behind one-dimensional Convolutional Neural Networks for text and sequences
19m 32s
Model 5: Building, fitting and evaluating a one-dimensional Convolutional Neural Network for text
9m 58s
Using TensorFlow Hub for pretrained word embeddings and transfer learning for Natural Language Processing
13m 45s
Model 6: Building, training and evaluating a transfer learning model for Natural Language Processing
10m 46s
Preparing subsets of data for Model 7, the same as Model 6 but with 10 percent of the data
10m 52s
Model 7: Building, training and evaluating a transfer learning model on 10 percent of the data
10m 4s
Fixing our data leakage issue with Model 7 and retraining it
13m 43s
Comparing all our modelling experiments evaluation metrics
13m 14s
Uploading our model's training logs to TensorBoard and comparing them
11m 15s
Saving and loading in a trained Natural Language Processing model with TensorFlow
10m 26s
Downloading a pretrained model and preparing data to investigate predictions
13m 25s
Visualizing our model's most wrong predictions
8m 29s
Making and visualizing predictions on the test dataset
8m 27s
Understanding the concept of the speed and score tradeoff
15m 2s

Overview

In this 62-hour course, build practical deep learning skill with TensorFlow across regression, classification, computer vision, NLP, transfer learning, and forecasting. Train, evaluate, improve, save, and explain models through hands-on experiments with real datasets.

What I will be able to do after this course

Build TensorFlow models for regression and classification
Manipulate tensors with TensorFlow and NumPy
Train CNNs for computer vision tasks
Apply transfer learning and fine-tuning workflows
Create NLP and time-series models with deep learning

Course Instructor(s)

Daniel is a self-taught Machine Learning Engineer and instructor with experience at Max Kelsen across healthcare, eCommerce, finance, retail, and other industries. His machine learning writing and videos have reached more than 5 million views, and he teaches with an accessible, practical style.

Who is it for?

This is for Python learners, aspiring machine learning engineers, data scientists, and developers who want hands-on TensorFlow practice. It suits learners ready to work through real projects in deep learning, computer vision, NLP, and forecasting.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Watch now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Python and TensorFlow: Deep dive into machine learning

Publisher Resources

ISBN: 9781808656712

Chapter 1 : Introduction

Chapter 2 : Deep Learning and TensorFlow Fundamentals

Chapter 3 : Neural Network Regression with TensorFlow

Chapter 4 : Neural Network Classification with TensorFlow

Chapter 5 : Computer Vision and Convolutional Neural Networks in TensorFlow

Chapter 6 : Transfer Learning in TensorFlow Part 1: Feature Extraction

Chapter 7 : Transfer Learning in TensorFlow Part 2: Fine-Tuning

Chapter 8 : Transfer Learning Part 3: Scaling Up

Chapter 9 : Milestone Project 1: Food Vision Big™

Chapter 10 : Natural Language Processing Fundamentals in TensorFlow

Chapter 11 : Milestone Project 2: SkimLit

Chapter 12 : Time Series Fundamentals in TensorFlow and Milestone Project 3: BitPredict

Chapter 13 : Where To Go From Here?

Chapter 14 : Appendix: Machine Learning Primer

Chapter 15 : Appendix: Machine Learning and Data Science Framework

Chapter 16 : Appendix: Pandas for Data Analysis

Chapter 17 : Appendix: NumPy

Overview

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,and much more.

More than 5,000 organizations count on O’Reilly

Julian F.

Addison B.

Amir M.

Mark W.

You might also like

Python and TensorFlow: Deep dive into machine learning

Complete Python Developer in 2026: Zero to Mastery

Learn Enough Python to be Dangerous: A Tutorial Introduction to Programming with Python

AWS Certified Cloud Practitioner CLF-CO2 Ultimate guide

Publisher Resources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.