Learning Path: TensorFlow: The Road to TensorFlow Second Edition
Course
Online
Description
-
Type
Course
-
Methodology
Online
-
Start date
Different dates available
Discover deep learning and machine learning with Python and TensorFlowPackt’s Video Learning Paths are a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it.It can be hard to get started with machine learning, particularly as new frameworks like TensorFlow start to gain traction across enterprise companies. TensorFlow is an open source software library for numerical computation using data flow graphs. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.This Learning Path begins by covering a mastery on Python with a deep focus on unlocking Python’s secrets. We then move on to understand deep learning as implemented by Python and TensorFlow. Finally, we solve common commercial machine learning problems using TensorFlow.If you have no prior exposure to one of the most important trends impacting how we do data science in the next few years, this Learning Path will help you get up to speed.The goal of this Learning Path is to help you understand deep learning and machine learning by getting to know Python first and then TensorFlow.This Learning Path is authored by some of the best in their fields.About the AuthorsDaniel ArbuckleDaniel Arbuckle got his Ph.D. In Computer Science from the University of Southern California. He has published numerous papers, along with several books and video courses, and is both a teacher of computer science and a professional programmer.Eder Santana
.
Eder Santana is a Ph.D. candidate in Electrical and Computer Engineering. After working for 3 years with kernel machines (SVMs, Information Theoretic Learning, and so on), Eder moved to the field of deep learning 2.5 years ago, when he started learning Theano, Caffe, and other machine learning frameworks. Now, Eder contributes to Keras, the deep learning library for Python
Facilities
Location
Start date
Start date
About this course
Build Python packages to efficiently create reusable code
Become proficient at creating tools and utility programs in Python
Design and train a multilayer neural network with TensorFlow
Understand convolutional neural networks for image recognition
Create pipelines to deal with real-world input data
Set up and run cross domain-specific examples (economics, medicine, text classification, and advertising)
Learn how to go from concept to a production-ready machine learning setup/pipeline capable of real-world usage
Reviews
This centre's achievements
All courses are up to date
The average rating is higher than 3.7
More than 50 reviews in the last 12 months
This centre has featured on Emagister for 4 years
Subjects
- Install
- Programming
- Writing
- Web
- Syntax
- Server
- Testing
Course programme
- Understand basic grammar elements
- Understand functions and classes
- Explain the reasoning behind Python's differences from other languages
- Learn to create data structures
- Learn how the structures organize data
- Learn to use comprehensions to operate on all members of a data structure
- Define first-class objects
- Explain the implications of first-class functions
- Explain the implications of first-class classes
- Take a look at data structures and data storage
- Understand encoding and decoding formats
- Interact with low-level operating system services
- Look at the syntax changes
- Understand the library additions
- Take a tour of the other changes
- Select the proper installer to download
- Install the Python runtime and libraries
- Test that everything is working correctly
- Open a command window
- Run the Python iterative shell
- Practice evaluating Python expressions
- Install packages
- Manage installed packages
- Search available packages
- Understand keyword searches
- Know browsing categories
- Look at searching through Pip
- Explore the relationship with filesystem directories
- Learn about __init__.py
- Try importing our new package
- Explore valid filenames for code modules
- Take a look at the contents of a code module
- Build up a programming interface from module parts
- Understand absolute imports
- Learn relative imports
- Check out how to avoid dependency cycles
- Understand where to put data files
- Use pkgutil.get_data
- Load text data
- Understand why tabs and spaces should not be mixed, and spaces are preferred
- Explain style conventions
- Explain naming conventions
- Initialize Git
- Use Git as an undo log
- Branch, merge, and pull
- Set up a virtual environment
- Activate a virtual environment
- Install packages locally in a virtual environment
- Understand basic docstring structure
- Understand reStructuredText for rich formatting
- Take a look at the Sphinx documentation compiler
- Understand how to write examples
- Learn how to check examples with doctest
- If the test fails, either the documentation is wrong or the code is; see how to rectify
- Understand what python-m means
- Take a look at the __main__ module
- Recognize when the program is being run and when it is being imported
- Instantiate an argument parser object
- Configure a argument parser object
- Access the parsed data
- Get to know the basics of print() and input()
- Get introduced to the special cases: getpass and pprint
- Work on interactive interfaces with the cmd package
- Know more about the subprocess.call function and its variants
- Get to know the subprocess.Popen class
- Communicate with a background process
- Create a shell script for Mac or Unix/Linux
- Create a batch file for Windows
- Use shell scripts or batch files to launch Python programs
- Learn the map and submit operations
- Understand Futures
- Know what to avoid for efficient data transfer between processes
- Get to know the Process class
- Learn inter-process communication
- Understand synchronization between processes
- See how coroutine scheduling operates in a single process
- Understand why coroutine scheduling has lower overhead per stream of execution
- Explore why coroutine scheduling is good for I/O bound programs, especially servers
- Get the default scheduler
- Add coroutine tasks to the scheduler
- Run the scheduler to execute the tasks
- Wait for Future to arrive and retrieve the value
- Check if Future has arrived, then retrieve the value
- Loop over a sequence of Future data
- Know the standard synchronization primitives
- Understand why synchronization is not always needed
- Use queues for inter-coroutine communication
- Create a client
- Create a server
- Know when to stop serving a client
- Understand what is a decorator and what does it does
- Define a wrapper inside a decorator
- Understand parameterized decorators
- Add metadata about function parameters
- Add metadata about the function's return value
- Annotations as input to function decorators
- Know that class decorators work just like function decorators
- Understand that classes are not functions, so the possibilities are different
- Rewrite classes as they're defined
- Understand that classes are objects, and these objects are instances of other classes
- Control class object creation
- Make custom handling inheritable
- Context managers plug into the with statement
- Know the two ways to define a synchronous context manager
- Understand that asynchronous context managers are also an option
- Use @property to create simple descriptors
- Write descriptors as classes
- Apply descriptors to simplify a complex I/O task
- See how automated testing makes it quick and easy to run tests
- Understand why tests can motivate development rather than the other way around
- Check out that when we reduce the difficulty and increase the frequency, tests are more useful
- Learn how we structure a test file
- Know how to compare what happens to what should happen
- Learn we run our tests
- Replace an object with a mock
- Make a mock object imitate the behavior of a real object.
- Check whether a mock object is a user
- Too many tests in one file becomes a problem, so break it up
- See why running each test individually would be annoying
- Take a look at the test discovery tool that finds all the tests and runs them
- Run tests with Nose
- Get a code coverage report
- Run tests in parallel
- Publish/subscribe event handling
- Understand stateless functional composition
- Learn asynchronous execution
- Wiring Observable
- Write Observer
- Write a demo application
- Install RxPY
- Translate our demo
- Learn more RxPY features
Additional information
Learning Path: TensorFlow: The Road to TensorFlow Second Edition