At the start of May, I decided to get TensorFlow Developer Certified.
So I set myself upwith a curriculum to sharpen my skillsand took the certification turns out, I passed.
Let me tell you how I did it and how you’re able to too.
Hold on, what even is TensorFlow?
Its what Google uses to power all of its machine learning services.
Chances are, the machine youre reading this on has run some kind of TensorFlow before.
Okay, now we know what TensorFlow is, what is the TensorFlow Developer Certification?
And why might you be interested in it?
What is the TensorFlow Developer Certification?
Why might you want to get TensorFlow Developer Certified?
My first reason was fun.
I want to be clear, a paid certificate is no guarantee of getting a job.
So how do you do it?
From these two resources, I built the following curriculum.
The beginner will want to take as much time as needed.
Remember: building any worthwhile skill takes time.
The timelines are based on my experience.
If you want to create a curriculum for yourself, Id recommend something like the following.
Note:For paid resources, affiliate links have been used.
1.The TensorFlow Developer Certification Handbook
Time:1-hour.
Helpfulness level:Required.
This should be your first stop.
It outlines the topics which will be covered in the exam.
Read it and then read it again.
The resources below will help you become familiar with them.
Cost:$59 per month after a 7-day free trial, financial aid available through app.
If you cant access Coursera, see theequivalent free version on YouTube.
This is the most relevant resource to the exam (and getting started with TensorFlow in general).
The careful student will notice the TensorFlow Certification handbook and the outline of this specialization are almost identical.
I appreciated the short video format and focus on hands-on examples as soon as possible.
The multiple code notebooks at the end of each section were must-haves for any practical learner.
Cost:Price varies on Amazon but I picked up a hard copy for $55.
it’s possible for you to see all thecode for free on GitHub.
Helpfulness level:7/10 (only because some chapters arent relevant to the exam).
Again, not to worry, youre not in a rush, learning useful skills takes time.
World-class deep learning information from a world-class university, oh and did I mention?
But again, for the eager learner, going through the whole course wouldnt be a bad idea.
Be sure to check out the labs and code they offer on GitHub, especially theIntroduction to TensorFlow one.
And again, I cant stress the importance of writing the code yourself.
5.Getting started with PyCharm
Time:3-hours (depending on how fast your rig is).
Helpfulness level:10/10 (using PyCharm is a requirement).
The exam takes place in PyCharm (a Python development tool).
Before the exam, Id never used PyCharm.
And its suggested you get at least somewhat familiar with it before you jump in.
Extras
How did I prepare for the exam?
Armed with the resources above, I put together anoutline in Notion.
This tribrid approach turned out to work particularly well.
Examination details what happens during the actual exam?
So youve done your study?
Well, lets start with two important factors.
Without the error at the start of the exam, Id say I wouldve comfortably completed it within 3-hours.
How is the exam structured?
Im not going to reveal much here because that would be cheating.
My broken Python interpreter The exam preparation material stresses that Python 3.7 is required for the exam.
When I started, I had Python 3.7.3.
2.0.0 -> 2.2.x).
After implementing the fix I was able to complete the exam with no issues.
What happens after you finish the exam?
Youll get notified via email when/if you passed the exam.
There will be no feedback except Congratulations you passed or Unfortunately you didnt pass this time.
But if you do pass congratulations!
Two things you might add alongside the projects youve worked on.
At the end of the day, skills are what you should be after, not certificates.
Certificates arenice to havenotneed to have.
If you say certificates arent needed, whyd you get it?
I like having a challenge to work towards.
Can I do this with free resources?
Yes, of course you’ve got the option to.
But they dont offer certification, if they did, Id probably do it too (for fun).
If anything, TensorFlow has an edge in the enterprise world (see graph above).
I dont know any machine learning, where can I start?
Read the article5 Beginner-Friendly Steps to Learn Machine Learning.
Ive passed the exam, and registered with the Google Developers Certification web connection, what do I next?
Use the skills youve learned to make something youd like to see in the world.
And dont forget to share your work, you never know wholl see it.
And if you prefer to watch things, I made avideo version of this article.
This article was written by Daniel Bourke and was originally published onTowards Data Science.
you’ve got the option to read ithere.
