TensorFlow Developer Certificate in 2021: Zero to Mastery

Introduction
1 Course Outline
2 Join Our Online Classroom!
3 Exercise Meet The Community
4 All Course Resources + Notebooks

Deep Learning and TensorFlow Fundamentals
5 What is deep learning
6 Why use deep learning
7 What are neural networks
8 What is deep learning already being used for
9 What is and why use TensorFlow
10 What is a Tensor
11 What we’re going to cover throughout the course
12 How to approach this course
13 Need A Refresher
14 Creating your first tensors with TensorFlow and tf.constant()
15 Creating tensors with TensorFlow and tf.Variable()
16 Creating random tensors with TensorFlow
17 Shuffling the order of tensors
18 Creating tensors from NumPy arrays
19 Getting information from your tensors (tensor attributes)
20 Indexing and expanding tensors
21 Manipulating tensors with basic operations
22 Matrix multiplication with tensors part 1
23 Matrix multiplication with tensors part 2
24 Matrix multiplication with tensors part 3
25 Changing the datatype of tensors
26 Tensor aggregation (finding the min, max, mean & more)
27 Tensor troubleshooting example (updating tensor datatypes)
28 Finding the positional minimum and maximum of a tensor (argmin and argmax)
29 Squeezing a tensor (removing all 1-dimension axes)
30 One-hot encoding tensors
31 Trying out more tensor math operations
32 Exploring TensorFlow and NumPy’s compatibility
33 Making sure our tensor operations run really fast on GPUs
34 TensorFlow Fundamentals challenge, exercises & extra-curriculum
35 Python + Machine Learning Monthly
36 LinkedIn Endorsements

Neural network regression with TensorFlow
37 Introduction to Neural Network Regression with TensorFlow
38 Inputs and outputs of a neural network regression model
39 Anatomy and architecture of a neural network regression model
40 Creating sample regression data (so we can model it)
41 The major steps in modelling with TensorFlow
42 Steps in improving a model with TensorFlow part 1
43 Steps in improving a model with TensorFlow part 2
44 Steps in improving a model with TensorFlow part 3
45 Evaluating a TensorFlow model part 1 ( visualise, visualise, visualise )
46 Evaluating a TensorFlow model part 2 (the three datasets)
47 Evaluating a TensorFlow model part 3 (getting a model summary)
48 Evaluating a TensorFlow model part 4 (visualising a model’s layers)
49 Evaluating a TensorFlow model part 5 (visualising a model’s predictions)
50 Evaluating a TensorFlow model part 6 (common regression evaluation metrics)
51 Evaluating a TensorFlow regression model part 7 (mean absolute error)
52 Evaluating a TensorFlow regression model part 7 (mean square error)
53 Setting up TensorFlow modelling experiments part 1 (start with a simple model)
54 Setting up TensorFlow modelling experiments part 2 (increasing complexity)
55 Comparing and tracking your TensorFlow modelling experiments
56 How to save a TensorFlow model
57 How to load and use a saved TensorFlow model
58 (Optional) How to save and download files from Google Colab
59 Putting together what we’ve learned part 1 (preparing a dataset)
60 Putting together what we’ve learned part 2 (building a regression model)
61 Putting together what we’ve learned part 3 (improving our regression model)
62 Preprocessing data with feature scaling part 1 (what is feature scaling )
63 Preprocessing data with feature scaling part 2 (normalising our data)
64 Preprocessing data with feature scaling part 3 (fitting a model on scaled data)
65 TensorFlow Regression challenge, exercises & extra-curriculum

Neural network classification in TensorFlow
66 Introduction to neural network classification in TensorFlow
67 Example classification problems (and their inputs and outputs)
68 Input and output tensors of classification problems
69 Typical architecture of neural network classification models with TensorFlow
70 Creating and viewing classification data to model
71 Checking the input and output shapes of our classification data
72 Building a not very good classification model with TensorFlow
73 Trying to improve our not very good classification model
74 Creating a function to view our model’s not so good predictions
75 Make our poor classification model work for a regression dataset
76 Non-linearity part 1 Straight lines and non-straight lines
77 Non-linearity part 2 Building our first neural network with non-linearity
78 Non-linearity part 3 Upgrading our non-linear model with more layers
79 Non-linearity part 4 Modelling our non-linear data once and for all
80 Non-linearity part 5 Replicating non-linear activation functions from scratch
81 Getting great results in less time by tweaking the learning rate
82 Using the TensorFlow History object to plot a model’s loss curves
83 Using callbacks to find a model’s ideal learning rate
84 Training and evaluating a model with an ideal learning rate
85 Introducing more classification evaluation methods
86 Finding the accuracy of our classification model
87 Creating our first confusion matrix (to see where our model is getting confused)
88 Making our confusion matrix prettier
89 Putting things together with multi-class classification part 1 Getting the data
90 Multi-class classification part 2 Becoming one with the data
91 Multi-class classification part 3 Building a multi-class classification model
92 Multi-class classification part 4 Improving performance with normalisation
93 Multi-class classification part 5 Comparing normalised and non-normalised data
94 Multi-class classification part 6 Finding the ideal learning rate
95 Multi-class classification part 7 Evaluating our model
96 Multi-class classification part 8 Creating a confusion matrix
97 Multi-class classification part 9 Visualising random model predictions
98 What patterns is our model learning
99 TensorFlow classification challenge, exercises & extra-curriculum

Computer Vision and Convolutional Neural Networks in TensorFlow
100 Introduction to Computer Vision with TensorFlow
101 Introduction to Convolutional Neural Networks (CNNs) with TensorFlow
102 Downloading an image dataset for our first Food Vision model
103 Becoming One With Data
104 Becoming One With Data Part 2
105 Becoming One With Data Part 3
106 Building an end to end CNN Model
107 Using a GPU to run our CNN model 5x faster
108 Trying a non-CNN model on our image data
109 Improving our non-CNN model by adding more layers
110 Breaking our CNN model down part 1 Becoming one with the data
111 Breaking our CNN model down part 2 Preparing to load our data
112 Breaking our CNN model down part 3 Loading our data with ImageDataGenerator
113 Breaking our CNN model down part 4 Building a baseline CNN model
114 Breaking our CNN model down part 5 Looking inside a Conv2D layer
115 Breaking our CNN model down part 6 Compiling and fitting our baseline CNN
116 Breaking our CNN model down part 7 Evaluating our CNN’s training curves
117 Breaking our CNN model down part 8 Reducing overfitting with Max Pooling
118 Breaking our CNN model down part 9 Reducing overfitting with data augmentation
119 Breaking our CNN model down part 10 Visualizing our augmented data
120 Breaking our CNN model down part 11 Training a CNN model on augmented data
121 Breaking our CNN model down part 12 Discovering the power of shuffling data
122 Breaking our CNN model down part 13 Exploring options to improve our model
123 Downloading a custom image to make predictions on
124 Writing a helper function to load and preprocessing custom images
125 Making a prediction on a custom image with our trained CNN
126 Multi-class CNN’s part 1 Becoming one with the data
127 Multi-class CNN’s part 2 Preparing our data (turning it into tensors)
128 Multi-class CNN’s part 3 Building a multi-class CNN model
129 Multi-class CNN’s part 4 Fitting a multi-class CNN model to the data
130 Multi-class CNN’s part 5 Evaluating our multi-class CNN model
131 Multi-class CNN’s part 6 Trying to fix overfitting by removing layers
132 Multi-class CNN’s part 7 Trying to fix overfitting with data augmentation
133 Multi-class CNN’s part 8 Things you could do to improve your CNN model
134 Multi-class CNN’s part 9 Making predictions with our model on custom images
135 Saving and loading our trained CNN model
136 TensorFlow computer vision and CNNs challenge, exercises & extra-curriculum

Transfer Learning in TensorFlow Part 1 Feature extraction
137 What is and why use transfer learning
138 Downloading and preparing data for our first transfer learning model
139 Introducing Callbacks in TensorFlow and making a callback to track our models
140 Exploring the TensorFlow Hub website for pretrained models
141 Building and compiling a TensorFlow Hub feature extraction model
142 Blowing our previous models out of the water with transfer learning
143 Plotting the loss curves of our ResNet feature extraction model
144 Building and training a pre-trained EfficientNet model on our data
145 Different Types of Transfer Learning
146 Comparing Our Model’s Results
147 TensorFlow Transfer Learning Part 1 challenge, exercises & extra-curriculum

Transfer Learning in TensorFlow Part 2 Fine tuning
148 Introduction to Transfer Learning in TensorFlow Part 2 Fine-tuning
149 Importing a script full of helper functions (and saving lots of space)
150 Downloading and turning our images into a TensorFlow BatchDataset
151 Discussing the four (actually five) modelling experiments we’re running
152 Comparing the TensorFlow Keras Sequential API versus the Functional API
153 Creating our first model with the TensorFlow Keras Functional API
154 Compiling and fitting our first Functional API model
155 Getting a feature vector from our trained model
156 Drilling into the concept of a feature vector (a learned representation)
157 Downloading and preparing the data for Model 1 (1 percent of training data)
158 Building a data augmentation layer to use inside our model
159 Visualising what happens when images pass through our data augmentation layer
160 Building Model 1 (with a data augmentation layer and 1% of training data)
161 Building Model 2 (with a data augmentation layer and 10% of training data)
162 Creating a ModelCheckpoint to save our model’s weights during training
163 Fitting and evaluating Model 2 (and saving its weights using ModelCheckpoint)
164 Loading and comparing saved weights to our existing trained Model 2
165 Preparing Model 3 (our first fine-tuned model)
166 Fitting and evaluating Model 3 (our first fine-tuned model)
167 Comparing our model’s results before and after fine-tuning
168 Downloading and preparing data for our biggest experiment yet (Model 4)
169 Preparing our final modelling experiment (Model 4)
170 Fine-tuning Model 4 on 100% of the training data and evaluating its results
171 Comparing our modelling experiment results in TensorBoard
172 How to view and delete previous TensorBoard experiments
173 Transfer Learning in TensorFlow Part 2 challenge, exercises and extra-curriculum

Transfer Learning with TensorFlow Part 3 Scaling Up
174 Introduction to Transfer Learning Part 3 Scaling Up
175 Getting helper functions ready and downloading data to model
176 Outlining the model we’re going to build and building a ModelCheckpoint callback
177 Creating a data augmentation layer to use with our model
178 Creating a headless EfficientNetB0 model with data augmentation built in
179 Fitting and evaluating our biggest transfer learning model yet
180 Unfreezing some layers in our base model to prepare for fine-tuning
181 Fine-tuning our feature extraction model and evaluating its performance
182 Saving and loading our trained model
183 Downloading a pretrained model to make and evaluate predictions with
184 Making predictions with our trained model on 25,250 test samples
185 Unravelling our test dataset for comparing ground truth labels to predictions
186 Confirming our model’s predictions are in the same order as the test labels
187 Creating a confusion matrix for our model’s 101 different classes
188 Evaluating every individual class in our dataset
189 Plotting our model’s F1-scores for each separate class
190 Creating a function to load and prepare images for making predictions
191 Making predictions on our test images and evaluating them
192 Discussing the benefits of finding your model’s most wrong predictions
193 Writing code to uncover our model’s most wrong predictions
194 Plotting and visualising the samples our model got most wrong
195 Making predictions on and plotting our own custom images
196 Transfer Learning in TensorFlow Part 3 challenge, exercises and extra-curriculum

Milestone Project 1 Food Vision Big™
197 Introduction to Milestone Project 1 Food Vision Big™
198 Making sure we have access to the right GPU for mixed precision training
199 Getting helper functions ready
200 Introduction to TensorFlow Datasets (TFDS)
201 Exploring and becoming one with the data (Food101 from TensorFlow Datasets)
202 Creating a preprocessing function to prepare our data for modelling
203 Batching and preparing our datasets (to make them run fast)
204 Exploring what happens when we batch and prefetch our data
205 Creating modelling callbacks for our feature extraction model
206 Turning on mixed precision training with TensorFlow
207 Creating a feature extraction model capable of using mixed precision training
208 Checking to see if our model is using mixed precision training layer by layer
209 Training and evaluating a feature extraction model (Food Vision Big™)
210 Introducing your Milestone Project 1 challenge build a model to beat DeepFood
211 Milestone Project 1 Food Vision Big™, exercises and extra-curriculum

NLP Fundamentals in TensorFlow
212 Welcome to natural language processing with TensorFlow!
213 Introduction to Natural Language Processing (NLP) and Sequence Problems
214 Example NLP inputs and outputs
215 The typical architecture of a Recurrent Neural Network (RNN)
216 Preparing a notebook for our first NLP with TensorFlow project
217 Becoming one with the data and visualising a text dataset
218 Splitting data into training and validation sets
219 Converting text data to numbers using tokenisation and embeddings (overview)
220 Setting up a TensorFlow TextVectorization layer to convert text to numbers
221 Mapping the TextVectorization layer to text data and turning it into numbers
222 Creating an Embedding layer to turn tokenised text into embedding vectors
223 Discussing the various modelling experiments we’re going to run
224 Model 0 Building a baseline model to try and improve upon
225 Creating a function to track and evaluate our model’s results
226 Model 1 Building, fitting and evaluating our first deep model on text data
227 Visualising our model’s learned word embeddings with TensorFlow’s projector tool
228 High-level overview of Recurrent Neural Networks (RNNs) + where to learn more
229 Model 2 Building, fitting and evaluating our first TensorFlow RNN model (LSTM)
230 Model 3 Building, fitting and evaluating a GRU-cell powered RNN
231 Model 4 Building, fitting and evaluating a bidirectional RNN model
232 Discussing the intuition behind Conv1D neural networks for text and sequences
233 Model 5 Building, fitting and evaluating a 1D CNN for text
234 Using TensorFlow Hub for pretrained word embeddings (transfer learning for NLP)
235 Model 6 Building, training and evaluating a transfer learning model for NLP
236 Preparing subsets of data for model 7 (same as model 6 but 10% of data)
237 Model 7 Building, training and evaluating a transfer learning model on 10% data
238 Fixing our data leakage issue with model 7 and retraining it
239 Comparing all our modelling experiments evaluation metrics
240 Uploading our model’s training logs to TensorBoard and comparing them
241 Saving and loading in a trained NLP model with TensorFlow
242 Downloading a pretrained model and preparing data to investigate predictions
243 Visualising our model’s most wrong predictions
244 Making and visualising predictions on the test dataset
245 Understanding the concept of the speed score tradeoff
246 NLP Fundamentals in TensorFlow challenge, exercises and extra-curriculum

Milestone Project 2 SkimLit
247 Introduction to Milestone Project 2 SkimLit
248 What we’re going to cover in Milestone Project 2 (NLP for medical abstracts)
249 SkimLit inputs and outputs
250 Setting up our notebook for Milestone Project 2 (getting the data)
251 Visualising examples from the dataset (becoming one with the data)
252 Writing a preprocessing function to structure our data for modelling
253 Performing visual data analysis on our preprocessed text
254 Turning our target labels into numbers (ML models require numbers)
255 Model 0 Creating, fitting and evaluating a baseline model for SkimLit
256 Preparing our data for deep sequence models
257 Creating a text vectoriser to map our tokens (text) to numbers
258 Creating a custom token embedding layer with TensorFlow
259 Creating fast loading dataset with the TensorFlow tf.data API
260 Model 1 Building, fitting and evaluating a Conv1D with token embeddings
261 Preparing a pretrained embedding layer from TensorFlow Hub for Model 2
262 Model 2 Building, fitting and evaluating a Conv1D model with token embeddings
263 Creating a character-level tokeniser with TensorFlow’s TextVectorization layer
264 Creating a character-level embedding layer with tf.keras.layers.Embedding
265 Model 3 Building, fitting and evaluating a Conv1D model on character embeddings
266 Discussing how we’re going to build Model 4 (character + token embeddings)
267 Model 4 Building a multi-input model (hybrid token + character embeddings)
268 Model 4 Plotting and visually exploring different data inputs
269 Crafting multi-input fast loading tf.data datasets for Model 4
270 Model 4 Building, fitting and evaluating a hybrid embedding model
271 Model 5 Adding positional embeddings via feature engineering (overview)
272 Encoding the line number feature to used with Model 5
273 Encoding the total lines feature to be used with Model 5
274 Model 5 Building the foundations of a tribrid embedding model
275 Model 5 Completing the build of a tribrid embedding model for sequences
276 Visually inspecting the architecture of our tribrid embedding model
277 Creating multi-level data input pipelines for Model 5 with the tf.data API
278 Bringing SkimLit to life!!! (fitting and evaluating Model 5)
279 Comparing the performance of all of our modelling experiments
280 Saving, loading & testing our best performing model
281 Congratulations and your challenge before heading to the next module
282 Milestone Project 2 (SkimLit) challenge, exercises and extra-curriculum

Time Series fundamentals in TensorFlow
283 More Videos Coming Soon!

Milestone Project 3 BitPredict
284 More Videos Coming Soon!

Passing the TensorFlow Developer Certificate Exam
285 More Videos Coming Soon!

Where To Go From Here
286 Become An Alumni
287 LinkedIn Endorsements
288 TensorFlow Certificate

Appendix Machine Learning Primer
289 Quick Note Upcoming Videos
290 What is Machine Learning
291 AI Machine Learning Data Science
292 Exercise Machine Learning Playground
293 How Did We Get Here
294 Exercise YouTube Recommendation Engine
295 Types of Machine Learning
296 Are You Getting It Yet
297 What Is Machine Learning Round 2
298 Section Review

Appendix Machine Learning and Data Science Framework
299 Quick Note Upcoming Videos
300 Section Overview
301 Introducing Our Framework
302 Step Machine Learning Framework
303 Types of Machine Learning Problems
304 Types of Data
305 Types of Evaluation
306 Features In Data
307 Modelling – Splitting Data
308 Modelling – Picking the Model
309 Modelling – Tuning
310 Modelling – Comparison
311 Overfitting and Underfitting Definitions
312 Experimentation
313 Tools We Will Use
314 Optional Elements of AI

Appendix Pandas for Data Analysis
315 Quick Note Upcoming Videos
316 Section Overview
317 Downloading Workbooks and Assignments
318 Pandas Introduction
319 Series, Data Frames and CSVs
320 Data from URLs
321 Describing Data with Pandas
322 Selecting and Viewing Data with Pandas
323 Selecting and Viewing Data with Pandas Part 2
324 Manipulating Data
325 Manipulating Data 2
326 Manipulating Data 3
327 Assignment Pandas Practice
328 How To Download The Course Assignments

Appendix NumPy
329 Quick Note Upcoming Videos
330 Section Overview
331 NumPy Introduction
332 Quick Note Correction In Next Video
333 NumPy DataTypes and Attributes
334 Creating NumPy Arrays
335 NumPy Random Seed
336 Viewing Arrays and Matrices
337 Manipulating Arrays
338 Manipulating Arrays 2
339 Standard Deviation and Variance
340 Reshape and Transpose
341 Dot Product vs Element Wise
342 Exercise Nut Butter Store Sales
343 Comparison Operators
344 Sorting Arrays
345 Turn Images Into NumPy Arrays
346 Assignment NumPy Practice
347 Optional Extra NumPy resources

BONUS SECTION
348 Special Bonus Lecture