Join SuperDataScience
Start Your Free Trial Today >>Welcome to Tensorflow 2.0!
Build Amazing Applications of Deep Learning and Artificial Intelligence in TensorFlow 2.0
When TensorFlow 2.0 was released 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.
Part 1: In Part 1 of the course, you will learn about the technology stack that we will use throughout the course (Introduction) and the TensorFlow 2.0 library basics and syntax (TensorFlow 2.0 Basics).
Part 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: Artificial Neural Networks, Convolutional Neural Network, and Recurrent Neural Network). At the end of this part, Transfer Learning and Fine Tuning, you will learn and build their own Transfer Learning application that achieves state of the art (SOTA) results on the Dogs vs. Cats dataset.
Part 3: 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: This part 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 Deep Reinforcement Learning for Stock Market trading 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 Data Validation with TensorFlow Data Validation (TFDV), we will make our own data preprocessing pipeline using the TensorFlow Transform library. In Dataset Preprocessing with TensorFlow Transform (TFT) 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 Fashion API with Flask and TensorFlow 2.0. 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 Image Classification API with TensorFlow Serving of the course, you will learn how to optimize and convert any neural network to be suitable for a mobile device.Part 5: To conclude with the learning process and the Part 5 of the course, in TensorFlow Lite: Prepare a model for a mobile device you will learn how to distribute the training of any Neural Network to multiple GPUs or even Servers using the TensorFlow 2.0 library.
This course is packed with practical exercises that are based on real-life case studies. So not only will you learn the theory, but you will also get lots of hands-on practice building your own models.
$35
/ MonthAccelerate your Career and boost your Earning Potential with our Expert Instructors & Community! What Youāll Unlock: - š 40+ Courses (over 200 hours!) - š 17 Specialized Career Paths - š Quizzes and Practice Activities - š Certificates for Courses & Career Paths - š Prizes for Learning - š§Ŗ Weekly Live Labs (plus recordings!) - šÆ Monthly Missions to practice even more - š¼ Monthly Career Booster Events - š¬ Full access to the SDS Community - ā” Monthly Speed Networking - š„ Monthly Resume Clinics - š„ Group Mentorship Program "In just a few months of learning at SDS, I landed a Data Analyst job!" ā Sanaz Afshar, California
$157
/ MonthAccelerate your Career and boost your Earning Potential with our Expert Instructors & Community! What Youāll Unlock: - š 40+ Courses (over 200 hours!) - š 17 Specialized Career Paths - š Quizzes and Practice Activities - š Certificates for Courses & Career Paths - š Prizes for Learning - š§Ŗ Weekly Live Labs (plus recordings!) - šÆ Monthly Missions to practice even more - š¼ Monthly Career Booster Events - š¬ Full access to the SDS Community - ā” Monthly Speed Networking - š„ Monthly Resume Clinics - š„ Group Mentorship Program Plus, Pro Plan perks just for you: - š A Personalized Career Path built around your goals - š§āš« 1-on-1 Mentoring Sessions every month - āļø Personalized Resume Reviews "In just a few months of learning at SDS, I landed a Data Analyst job!" ā Sanaz Afshar, California
Course content
What is Transfer Learning?
04:54
Project Setup
03:47
Dataset Preprocessing
05:51
Loading the MobileNet V2 Model
03:17
Freezing the Pre-trained Model
01:23
Adding a Custom Head to the Pre-trained Model
03:33
Defining the Transfer Learning Model
02:00
Compiling the Transfer Learning Model
02:56
Image Data Generators
05:31
Transfer Learning
02:28
Evaluating Transfer Learning Results
01:29
Fine Tuning Model Definition
04:01
Compiling the Fine Tuning Model
01:10
Fine Tuning
02:04
Evaluating Fine Tuning Results
01:31
Quiz: Transfer Learning
What is the TensorFlow Serving?
05:59
TensorFlow Serving Architecture
03:43
Project Setup
03:47
Dataset Preprocessing
04:25
Defining, Training and Evaluating a Model
03:00
Saving the Model for Production
04:49
Serving the TensorFlow 2.0 Model
04:03
Creating a JSON Object
03:01
Sending the First POST Request to the Model
05:44
Sending the POST Request to a Specific Model
02:12