01 – Introduction
001 Welcome to the TensorFlow 2.0 course! Discover its structure and the TF toolkit00:00:00
02 – TensorFlow 2.0 Basics
001 From TensorFlow 1.x to TensorFlow 2.000:00:00
002 Constants, Variables, Tensors00:00:00
003 Operations with Tensors00:00:00
004 Strings00:00:00
03 – Artificial Neural Networks
001 Project Setup00:00:00
002 Data Preprocessing00:00:00
003 Building the Artificial Neural Network00:00:00
004 Training the Artificial Neural Network00:00:00
005 Evaluating the Artificial Neural Network00:00:00
04 – Convolutional Neural Networks
001 Project Setup & Data Preprocessing00:00:00
002 Building the Convolutional Neural Network00:00:00
003 Training and Evaluating the Convolutional Neural Network00:00:00
05 – Recurrent Neural Networks
001 Project Setup & Data Preprocessing00:00:00
002 Building the Recurrent Neural Network00:00:00
003 Training and Evaluating the Recurrent Neural Network00:00:00
06 – Transfer Learning and Fine Tuning
001 What is Transfer Learning00:00:00
002 Project Setup00:00:00
003 Dataset preprocessing00:00:00
004 Loading the MobileNet V2 model00:00:00
005 Freezing the pre-trained model00:00:00
006 Adding a custom head to the pre-trained model00:00:00
007 Defining the transfer learning model00:00:00
008 Compiling the Transfer Learning model00:00:00
009 Image Data Generators00:00:00
010 Transfer Learning00:00:00
011 Evaluating Transfer Learning results00:00:00
012 Fine Tuning model definition00:00:00
013 Compiling the Fine Tuning model00:00:00
014 Fine Tuning00:00:00
015 Evaluating Fine Tuning results00:00:00
07 – Deep Reinforcement Learning Theory
001 What is Reinforcement Learning00:00:00
002 The Bellman Equation00:00:00
003 Markov Decision Process (MDP)00:00:00
004 Q-Learning Intuition00:00:00
005 Temporal Difference00:00:00
006 Deep Q-Learning Intuition – Step 100:00:00
007 Deep Q-Learning Intuition – Step 200:00:00
008 Experience Replay00:00:00
009 Action Selection Policies00:00:00
08 – Deep Reinforcement Learning for Stock Market trading
001 Project Setup00:00:00
002 AI Trader – Step 100:00:00
003 AI Trader – Step 200:00:00
004 AI Trader – Step 300:00:00
005 AI Trader – Step 400:00:00
006 AI Trader – Step 500:00:00
007 Dataset Loader function00:00:00
008 State creator function00:00:00
009 Loading the dataset00:00:00
010 Defining the model00:00:00
011 Training loop – Step 100:00:00
012 Training loop – Step 200:00:00
09 – Data Validation with TensorFlow Data Validation (TFDV)
001 Project Setup00:00:00
002 Loading the pollution dataset.00:00:00
003 Creating dataset Schema00:00:00
004 Computing test set statistics00:00:00
005 Anomaly detection with TensorFlow Data Validation00:00:00
006 Preparing Schema for production.00:00:00
007 Saving the Schema00:00:00
10 – Dataset Preprocessing with TensorFlow Transform (TFT)
001 Project Setup00:00:00
002 Initial dataset preprocessing00:00:00
003 Dataset metadata00:00:00
004 Preprocessing function00:00:00
005 Dataset preprocessing pipeline00:00:00
11 – Fashion API with Flask and TensorFlow 2.0
001 Project Setup00:00:00
002 Importing project dependencies00:00:00
003 Loading a pre-trained model00:00:00
004 Defining the Flask application00:00:00
005 Creating classify function00:00:00
006 Starting the Flask application00:00:00
007 Sending API requests over internet to the model00:00:00
12 – Image Classification API with TensorFlow Serving
001 What is the TensorFlow Serving00:00:00
002 TensorFlow Serving architecture00:00:00
003 Project setup00:00:00
004 Dataset preprocessing00:00:00
005 Defining, training and evaluating a model00:00:00
006 Saving the model for production00:00:00
007 Serving the TensorFlow 2.0 Model00:00:00
008 Creating a JSON object00:00:00
009 Sending the first POST request to the model00:00:00
010 Sending the POST request to a specific model00:00:00
13 – TensorFlow Lite Prepare a model for a mobile device
001 What is the TensorFlow Lite00:00:00
002 Project setup00:00:00
003 Dataset preprocessing00:00:00
004 Building a model00:00:00
005 Training, evaluating the model00:00:00
006 Saving the model00:00:00
007 TensorFlow Lite Converter00:00:00
008 Converting the model to a TensorFlow Lite model00:00:00
009 Saving the converted model00:00:00
14 – Distributed Training with TensorFlow 2.0
001 What is the Distributed Training00:00:00
002 Project Setup00:00:00
003 Dataset preprocessing00:00:00
004 Defining a non-distributed model (normal CNN model)00:00:00
005 Setting up a distributed strategy00:00:00
006 Defining a distributed model00:00:00
007 Final evaluation – Speed test normal model vs distributed model00:00:00
15 – Annex 1 – Artificial Neural Networks Theory
001 Plan of Attack00:00:00
002 The Neuron00:00:00
003 The Activation Function00:00:00
004 How do Neural Networks Work00:00:00
005 How do Neural Networks Learn00:00:00
006 Gradient Descent00:00:00
007 Stochastic Gradient Descent.00:00:00
008 Backpropagation00:00:00
16 – Annex 2 – Convolutional Neural Networks Theory
001 Plan of Attack00:00:00
002 What are Convolutional Neural Networks00:00:00
003 Step 1 – Convolution00:00:00
004 Step 1 Bis – ReLU Layer00:00:00
005 Step 2 – Max Pooling00:00:00
006 Step 3 – Flattening00:00:00
007 Step 4 – Full Connection00:00:00
008 Summary00:00:00
009 Softmax & Cross-Entropy009 Softmax & Cross-Entropy00:00:00
17 – Annex 3 – Recurrent Neural Networks Theory
001 Plan of Attack00:00:00
002 What are Recurrent Neural Networks00:00:00
003 Vanishing Gradient00:00:00
004 LSTMs00:00:00
005 LSTM Practical Intuition00:00:00
006 LSTM Variations00:00:00