A Complete Guide on TensorFlow 2.0 using Keras API

Build Amazing Applications of Deep Learning and Artificial Intelligence in TensorFlow 2.0

4.43 (1939 reviews)
Udemy
platform
English
language
Data Science
category
54,634
students
13 hours
content
Mar 2024
last update
$89.99
regular price

What you will learn

How to use Tensorflow 2.0 in Data Science

Important differences between Tensorflow 1.x and Tensorflow 2.0

How to implement Artificial Neural Networks in Tensorflow 2.0

How to implement Convolutional Neural Networks in Tensorflow 2.0

How to implement Recurrent Neural Networks in Tensorflow 2.0

How to build your own Transfer Learning application in Tensorflow 2.0

How to build a stock market trading bot using Reinforcement Learning (Deep-Q Network)

How to build Machine Learning Pipeline in Tensorflow 2.0

How to conduct Data Validation and Dataset Preprocessing using TensorFlow Data Validation and TensorFlow Transform.

Putting a TensorFlow 2.0 model into production

How to create a Fashion API with Flask and TensorFlow 2.0

How to serve a TensorFlow model with RESTful API

Description

Welcome to Tensorflow 2.0!


TensorFlow 2.0 has just been released, and it introduced many features that simplify the model development and maintenance processes. From the educational side, it boosts people's understanding by simplifying many complex concepts. From the industry point of view, models are much easier to understand, maintain, and develop.


Deep Learning is one of the fastest growing areas of Artificial Intelligence. In the past few years, we have proven that Deep Learning models, even the simplest ones, can solve very hard and complex tasks. Now, that the buzz-word period of Deep Learning has, partially, passed, people are releasing its power and potential for their product improvements.


The course is structured in a way to cover all topics from neural network modeling and training to put it in production.


In Part 1 of the course, you will learn about the technology stack that we will use throughout the course (Section 1) and the TensorFlow 2.0 library basics and syntax (Section 2).


In Part 2 of the course, we will dig into the exciting world of deep learning. Through this part of the course, you will implement several types of neural networks (Fully Connected Neural Network (Section 3), Convolutional Neural Network (Section 4), Recurrent Neural Network (Section 5)). At the end of this part, Section 6, you will learn and build their own Transfer Learning application that achieves state of the art (SOTA) results on the Dogs vs. Cats dataset.


After passing the part 2 of the course and ultimately learning how to implement neural networks, in Part 3 of the course, you will learn how to make your own Stock Market trading bot using Reinforcement Learning, specifically Deep-Q Network.


Part 4 is all about TensorFlow Extended (TFX). In this part of the course, you will learn how to work with data and create your own data pipelines for production. In Section 8 we will check if the dataset has any anomalies using the TensorFlow Data Validation library and after learn how to check a dataset for anomalies, in Section 9, we will make our own data preprocessing pipeline using the TensorFlow Transform library.


In Section 10 of the course, you will learn and create your own Fashion API using the Flask Python library and a pre-trained model. Throughout this section, you will get a better picture of how to send a request to a model over the internet. However, at this stage, the architecture around the model is not scalable to millions of request. Enter the Section 11. In this section of the course, you will learn how to improve solution from the previous section by using the TensorFlow Serving library. In a very easy way, you will learn and create your own Image Classification API that can support millions of requests per day!


These days it is becoming more and more popular to have a Deep Learning model inside an Android or iOS application, but neural networks require a lot of power and resources! That's where the TensorFlow Lite library comes into play. In Section 12 of the course, you will learn how to optimize and convert any neural network to be suitable for a mobile device.


To conclude with the learning process and the Part 5 of the course, in Section 13 you will learn how to distribute the training of any Neural Network to multiple GPUs or even Servers using the TensorFlow 2.0 library.



Content

Introduction

Welcome to the TensorFlow 2.0 course! Discover its structure and the TF toolkit.
Course Curriculum & Colab Toolkit
BONUS: 10 advantages of TensorFlow

TensorFlow 2.0 Basics

From TensorFlow 1.x to TensorFlow 2.0
Constants, Variables, Tensors
Operations with Tensors
Strings

Artificial Neural Networks

Project Setup
Data Preprocessing
Building the Artificial Neural Network
Training the Artificial Neural Network
Evaluating the Artificial Neural Network
Artificial Neural Network Quiz
HOMEWORK: Artificial Neural Networks
HOMEWORK SOLUTION: Artificial Neural Networks

Convolutional Neural Networks

Project Setup & Data Preprocessing
Building the Convolutional Neural Network
Training and Evaluating the Convolutional Neural Network
Convolutional Neural Networks Quiz
HOMEWORK: Convolutional Neural Networks
HOMEWORK SOLUTION: Convolutional Neural Networks

Recurrent Neural Networks

Project Setup & Data Preprocessing
Building the Recurrent Neural Network
Training and Evaluating the Recurrent Neural Network
Recurrent Neural Network Quiz

Transfer Learning and Fine Tuning

What is Transfer Learning?
Project Setup
Dataset preprocessing
Loading the MobileNet V2 model
Freezing the pre-trained model
Adding a custom head to the pre-trained model
Defining the transfer learning model
Compiling the Transfer Learning model
Image Data Generators
Transfer Learning
Evaluating Transfer Learning results
Fine Tuning model definition
Compiling the Fine Tuning model
Fine Tuning
Evaluating Fine Tuning results
Transfer Learning quiz

Deep Reinforcement Learning Theory

What is Reinforcement Learning?
The Bellman Equation
Markov Decision Process (MDP)
Q-Learning Intuition
Temporal Difference
Deep Q-Learning Intuition - Step 1
Deep Q-Learning Intuition - Step 2
Experience Replay
Action Selection Policies

Deep Reinforcement Learning for Stock Market trading

Project Setup
AI Trader - Step 1
AI Trader - Step 2
AI Trader - Step 3
AI Trader - Step 4
AI Trader - Step 5
Dataset Loader function
State creator function
Loading the dataset
Defining the model
Training loop - Step 1
Training loop - Step 2

Data Validation with TensorFlow Data Validation (TFDV)

Project Setup
Loading the pollution dataset
Creating dataset Schema
Computing test set statistics
Anomaly detection with TensorFlow Data Validation
Preparing Schema for production
Saving the Schema
What's next?

Dataset Preprocessing with TensorFlow Transform (TFT)

Project Setup
Initial dataset preprocessing
Dataset metadata
Preprocessing function
Dataset preprocessing pipeline
What's next?

Fashion API with Flask and TensorFlow 2.0

Project Setup
Importing project dependencies
Loading a pre-trained model
Defining the Flask application
Creating classify function
Starting the Flask application
Sending API requests over internet to the model

Image Classification API with TensorFlow Serving

What is the TensorFlow Serving?
TensorFlow Serving architecture
Project setup
Dataset preprocessing
Defining, training and evaluating a model
Saving the model for production
Serving the TensorFlow 2.0 Model
Creating a JSON object
Sending the first POST request to the model
Sending the POST request to a specific model

TensorFlow Lite: Prepare a model for a mobile device

What is the TensorFlow Lite?
Project setup
Dataset preprocessing
Building a model
Training, evaluating the model
Saving the model
TensorFlow Lite Converter
Converting the model to a TensorFlow Lite model
Saving the converted model
What's next?

Distributed Training with TensorFlow 2.0

What is the Distributed Training?
Project Setup
Dataset preprocessing
Defining a non-distributed model (normal CNN model)
Setting up a distributed strategy
Defining a distributed model
Final evaluation - Speed test: normal model vs distributed model

Annex 1 - Artificial Neural Networks Theory

Plan of Attack
The Neuron
The Activation Function
How do Neural Networks Work?
How do Neural Networks Learn?
Gradient Descent
Stochastic Gradient Descent
Backpropagation

Annex 2 - Convolutional Neural Networks Theory

Plan of Attack
What are Convolutional Neural Networks?
Step 1 - Convolution
Step 1 Bis - ReLU Layer
Step 2 - Max Pooling
Step 3 - Flattening
Step 4 - Full Connection
Summary
Softmax & Cross-Entropy

Annex 3 - Recurrent Neural Networks Theory

Plan of Attack
What are Recurrent Neural Networks?
Vanishing Gradient
LSTMs
LSTM Practical Intuition
LSTM Variations

Bonus Lectures

***YOUR SPECIAL BONUS***

Screenshots

A Complete Guide on TensorFlow 2.0 using Keras API - Screenshot_01A Complete Guide on TensorFlow 2.0 using Keras API - Screenshot_02A Complete Guide on TensorFlow 2.0 using Keras API - Screenshot_03A Complete Guide on TensorFlow 2.0 using Keras API - Screenshot_04

Reviews

Matt
March 1, 2023
It's ok, seems like many of the scripts need to be redone. I can't run them on colab for various errors from libraries that have changed.
Varghese
February 25, 2023
The instructor is crystal clear about stuff and ensure that the listener grasped it to the core..amazing
William
February 17, 2023
for me it is a good primer for tf. I know quite a bit of it already. He does a very good job at a relatively high level.
Ofir
June 13, 2022
Quizzes were very few and mostly on syntax. There are almost no coding exercises. The notebooks are not working in some cases (versions changed and the pip installs are for the newest versions). I was able to solve most of the syntax problems. The videos are ok.
Andrew
June 1, 2022
A noble and insightful guide on the journey or adventure of learning TensorFlow 2.0 and very happy to learn this course.
Mohamed
March 27, 2022
Everything was easy but there was a little differences between the training video file and google colab
Kush
March 14, 2022
This is not a complete guide, rather an introduction. Nobody answers on the forum, there are so many unanswered questions. Code has not been maintained. Would not recommend it.
Carleton
March 12, 2022
This course probably needs to advertise itself as an intro-level course aimed at beginners in Python, ML, and Tensorflow. There's basically no theory, much of each sections and presenters share redundant information which wastes a ton of viewer time, the notebooks are outdated and libraries don't always work, and there's even an entire section pasted from a Pytorch course, which comes across as lazy. I really want to take some of the more 'advanced' courses from these instructors but the simplicity of this course is deterring me at the moment... If you're looking to learn Tensorflow 2, this course would be good to get a quick intro, and then I would quickly move onto "Hands on Machine Learning with Scikit-Learn and Tensorflow 2" by Aurélien Géron, which is much more in depth, and gives you more back for the time you spend reading and applying.
Dmitry
February 12, 2022
В курсе слишком много воды, чего только стоит проговаривание залогированных значений accuracy для каждой из эпох обучения.
Thomas
October 3, 2021
This course was perfect for me. It made everything look easy and answered many questions that have been troubling me. The course starts out by simplifying and organizing material that I have seen before. This presentation gave me a much greater insight in these topics. Next, the course introduced me to several new (to me) topics in the same highly intuitive and insightful manner. Finally, several topics were introduced which are somewhat advanced (for me) that will be of great interest in the future.
Anastasios
October 2, 2021
I am not a beginner with the TF but I've choose this courses mostly for the RL part, and the more advanced features of TF plus how to move a model into production.
Kai
June 11, 2021
Very good course for TensorfFlow 2.0. The only issue is the code for with TensorFlow Serving is no longer working.
Victor
June 7, 2021
Thanks, RNN part of the course was great to refresh my memories, and I'm glad to learn about the transfer learning, too.
Ranjith
June 2, 2021
Solid content and narrator elegantly walked us through various parts of tensorflow 2.0 and different deep learning model implementations!!!!
Steven
April 7, 2021
Very good and comprehensive course. I learned exactly what I needed to for right now. The examples were clear and easy to follow.

Coupons

DateDiscountStatus
4/10/2020100% OFF
expired
6/28/202092% OFF
expired
8/10/202092% OFF
expired
10/17/202092% OFF
expired

Charts

Price

A Complete Guide on TensorFlow 2.0 using Keras API - Price chart

Rating

A Complete Guide on TensorFlow 2.0 using Keras API - Ratings chart

Enrollment distribution

A Complete Guide on TensorFlow 2.0 using Keras API - Distribution chart
2400948
udemy ID
6/6/2019
course created date
8/31/2019
course indexed date
Bot
course submited by