In this multi-part series, we will explore how to get started with tensorflow. This tensorflow tutorial will lay a solid foundation to this popular tool that everyone seems to be talking about. The first part will focus on introducing tensorflow, go through some applications and touch upon the architecture.
This post is the first part of the multi-part series on a complete tensorflow tutorial –
Well, for starters, it is an open source library from Google. Tensorflow has been gaining a lot of traction in the market given the rising popularity of neural networks and deep learning.
Many applications as of today have tensorflow embedded as part of their machine learning applications. Some broad applications have been listed below –
Some of the most popular cutting edge real world applications are using tensorflow.
They have reported great accuracy scores which keeps on increasing over time.
An interface for expressing machine learning algorithms and an implementation for executing such algorithms; A framework for creating ensemble algorithms for today’s most challenging problems. – Google Brain Team
Tensorflow is not just a pre-defined library of algorithms that you can use out of the box. It is a low-level library where you can orchestrate and design complex algorithms. It is very flexible in the way it lets you define your own computation graph.
For people not wanting to leverage such low-level flexibilities, there is a rich set of pre-defined algorithms that you can use off the shelf. These algorithms have been the architectures used in latest research papers known to push accuracies to new levels.
So, in a way Transfer Learning (a feature of TensorFlow to be discussed later in the series) brings the Industry and Academia together.
Let’s explore the tensorflow environment and how the flexible architecture makes implementation so easy.
All technology components need an underlying programming language so that a programmer can talk to the technology. Tensorflow is one such technologies that requires SDKs in other programming languages to implement.
Right now, tensorflow supports the following only –
For all of this series, we will only be using the Python implementations to build our solutions. I will happily willing to make C++ additions in case someone is willing to contribute.
Once the computation graph has been specified, it is sent to the execution environment to be executed. The execution master uses process execution device commands, to determine where to execute code.
This means you can execute code locally in your laptop with a CPU of a GPU if you have one. It also means you can trigger remote execution to a distributed system with multiple nodes, CPUs and GPUs.
This means you can build code and try it out with small data in your local machine. If it works out, you can easily scale it across large clusters with very little effort on your part.
A tensor is an n-dimensional structure –
As in the above diagram, we start with two tensors a and b. Since these can be multi-dimensional arrays of data, they can be taken to be complex data objects – such as images. Therefore, it might produce an n-dimensional array – which might be the result of multiplying the pixels of the two images, although I am not sure what the output image might look like.
The result is then added with another multi-dimensional array c, which might result in varying brightness of the images perhaps (depends on whether c is positive or negative).
I will be referring to these computation graphs as simply graphs.
These tensors flow through and are altered by operations (multiply and add for example). The flow of these tensors through these operations is what renders the name tensorflow.
Skills Required | Skills Not Required |
Knowledge of at least 1 programming language | Expertise in TensorFlow |
Basic Math and Statistics | Expertise in Python |
Passion to Understand | Advanced Math and Statistics |
I hope this sets the expectations for what is about to come. In the next post we will talk about installing and a simple TensorFlow implementation.
Let me know your opinions in the comments section below.
Comment
Thank You very much for your reply !!
Hello Dr Kotrappa! I have actually published a full blown video based structured content at Udemy - https://www.udemy.com/tensorflow-getting-started/learn/v4/overview
It is very cheap and it provides a complete foundation to tensorflow in a self-paced course. It also contains all the exercise files as well.
If you are looking at codes only, I will share them separately with you of course - but the structured content will give them the complete picture.
For the codes only way, please send me an email at [email protected] and I will reply back with some sample codes used in the course as well as this blog series. Thanks!
Please can you share few simple projects for our Engineering (CS) students using TensorFlow for practice and learn !! Thank You
@Carl - ohh yes you caught me! thats a typo :)
@Manuel - within the coming week I plan to share two more! Will post the link for the subsequent posts in the comments. Stay tuned! :)
@Everyone - Apologies for not personally thanking everyone but your feedback means a lot to me. Thank you so much for the motivation!
Hello,
You post is very helpful for me. thanks for sharing it with us
Very nice start! Would be good to know when you are going to publish the next part.
well done. Do you have some github about your tutorial?
Thank you very much. A googles developers group Los Angeles is hosting a meetup.
Google Developer Group Los Angeles
Machine Learning and Tensor Flow with Josh Gordon of Google
https://www.meetup.com/gdg-la/events/243409890/
I will use your information to help me with this workshop and tensorflow.
© 2017 Data Science Central Powered by
Badges | Report an Issue | Privacy Policy | Terms of Service
You need to be a member of Data Science Central to add comments!
Join Data Science Central