The TensorFlow Develop Certificate was one of the many Milestones in my Journey into AI. At the end of July, I was nearing the start of my semester. I decided to prepare myself and take the TensorFlow Developer certification. And (August 12th) I took the test and passed.

Let me tell you how I did, I hope this helps you on your journey.

The day after the test.

But wait for a second, what is TensorFlow?

TensorFlow is an open-source numerical computing framework that allows you to preprocess data, model data (find patterns in it, typically with deep learning) and deploy your solutions to the world.

It is used by Google and many other companies to build Machine Learning products. It is typically written in python (this exam included) or javascript (tensorflow.js).

What is the TensorFlow Certification?

The TensorFlow Certification is the official exam by the TensorFlow team. As you may have guessed it, is a way you can showcase your ability in the field. This test is designed in a very comprehensive manner. It tests your ability to write python code to build deep-learning models for a range of tasks like regression, computer vision (finding patterns in images), natural language processing (finding patterns in text) and Time-series prediction (predicting future trends given a range of past events).

Why did I/you might want to get TensorFlow Developer Certified?

The first and primary reason I did was for fun. I really just wanted to see what it was about and whether I can challenge myself to do it.

Some other valid reasons include:

1. To acquire and learn the foundational skills to build ML-powered applications.
2. Showcasing your competency to a relevant employer.

Just to be clear, I have not done this course to land a job or internship (I’m available at this moment). I strongly believe that the skills of the individual and his projects have more weight. just that this is certificate is good to have but not must.

How did I prepare for the exam?

The first thing I did was go through the Certification website. And I also read the TensorFlow Developer Certification Handbook. I started out by using these 2 resources and planning my study accordingly.

Curriculum and what I studied

I have to say that, I have some prior knowledge of TensorFlow and I had some experience building deep-learning models before.

For an experienced TensorFlow practitioner you might go through the curriculum at the same pace as I did, and finish it in about 2-3 weeks (I took 15 days).

But for a beginner, I recommend you take the time and go through it slowly, understand each concept deeply. It may take longer, but keep yourself motivated you will learn a lot more.

If you want to create a curriculum for yourself, I’d recommend something like the following.

1. The TensorFlow Developer Certification Handbook

Time: 1-hour.

Cost: Free.

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.

If you’re new to TensorFlow and machine learning, you’ll likely read this and get scared at all the different topics. Don’t worry. The resources below will help you become familiar with them.

2. DeepLearning.AI TensorFlow Developer Professional Certificate on Coursera

Time: 3 weeks (advanced user) to 3 months (beginner).

Cost: About 4000 rupees per month after a 7-day free trial, financial aid available through the application. If you can’t access Coursera, see the equivalent free version on YouTube.

Helpfulness level: 10/10.

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.

It’s taught by Laurence Moroney and Andrew Ng, two titans of TensorFlow and machine learning and if I had to only choose one resource to prepare for the exam, this would be it.

I appreciated the short video format and the 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.

A tip for the programming exercises: don’t just fill in the code gaps, write the entire thing out yourself.

3. Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow 2nd Edition

Time: 3 weeks (reading cover to cover, no exercises) — 3 months (reading cover to cover and doing the exercises).

Cost: Price varies on Amazon but I picked up a hard copy for 1200 rupees at discount. You can see all the [code for free on GitHub].(https://github.com/ageron/handson-ml2).

Helpfulness level: 7/10 (only because some chapters aren’t relevant to the exam).

At 700+ pages, this book covers basically all of the machine learning and thus, some topics which aren’t relevant to the exam. But it’s a must-read for anyone interested in setting themselves a solid foundation for a future in machine learning and not just to pass an exam.

If you’re new to machine learning, you’ll probably find this book hard to read (to begin with). Again, not to worry, you’re not in a rush, learning useful skills takes time.

Put it this way, if you want an idea of the quality of the book, I read the first edition during morning commutes to my machine learning engineer job. And I can tell you, more often than not, I’d end up using exactly what I read in the book during the day.

If you’re only after relevant chapters to the exam, you’ll want to read:

• Chapter 10: Introduction to Artificial Neural Networks with Keras
• Chapter 11: Training Deep Neural Networks
• Chapter 12: Custom Models and Training with TensorFlow
• Chapter 13: Loading and Preprocessing Data with TensorFlow
• Chapter 14: Deep Computer Vision Using Convolutional Neural Networks
• Chapter 15: Processing Sequences Using RNNs and CNNs
• Chapter 16: Natural Language Processing with RNNs and Attention

But for the serious student, I’d suggest the whole book and the exercises (maybe not all, but pick and the choose the ones which suit spark your interests most).

4. Introduction to Deep Learning by MIT

Time: 3-hours (I only watched 3 lectures) — 24-hours (1-hour per lecture, plus 1-hour review each).

Cost: Free.

Helpfulness level: 8/10.

World-class deep learning information from a world-class university, oh and did I mention? It’s free.

The first 3 lectures, deep learning (in general), Convolutional Neural Networks (usually used for computer vision) and Recurrent Neural Networks (usually used for text processing) are the most relevant to the exam.

But again, for the eager learner, going through the whole course wouldn’t be a bad idea.

Be sure to check out the labs and code they offer on GitHub, especially the Introduction to TensorFlow one. And again, I can’t stress the importance of writing the code yourself.

Examination details – what happens during the actual exam?

So you’ve finished studying, now let’s start with two important factors.

Exam cost: $100 USD (per attempt, if you fail, you have to wait 2 weeks to try again and longer for each fail thereafter).

Time-limit: 5-hours. Without the error at the start of the exam, I’d say I would’ve comfortably completed it within 3-hours. However, the extended time limit is to give you enough time to train deep learning models on your computer (so make sure this works before starting. I finished it in 2 hours).

How is the exam structured?

I’m not going to reveal much here because that would be cheating. All I’ll say is read the TensorFlow Developer Handbook and you’ll get a fair idea of the major sections of the exam.

Practice each one of the techniques mentioned in the handbook (using the resources mentioned above) and you’ll be fine.

Exam Tips

Training models – If your computer can’t train deep learning models fast enough (part of the marking criteria is submitting trained models), you can train them in Google Colab using a free GPU, then download them, put them in the relevant directories for the exam and submit them through PyCharm. (this is how I was able to finish the exam in under 2 hours.)

Update – As of August 12 2021, the exam now requires TensorFlow 2.5 & Python 3.8, see the set up your environment handbook for more.

PyCharm – You are required to install precise versions of PyCharm and specific plugins so, be sure it works before hand. Be sure to practice with some sample code before you take the test.

What happens after you finish the exam?

You’ll get notified via email when/if you passed the exam. There will be no feedback except “Congratulations you passed” or “Unfortunately you didn’t pass this time”.

Without spoiling too much, you’ll get a pretty clear indication whilst taking the exam if you’re likely to pass or not (each time you submit a model, it gets marked).

There are 5 questions, each getting marked out of 5. Try to get the full 5/5 for all questions to guarantee that you will pass. (I did this)

If you do pass, congratulations!

Be sure to fill out the form in the email to make sure you get added the TensorFlow Certified Developers network.

Click on the image to view the accreditation.

Finally, within a few days, you’ll be emailed an official TensorFlow Developer Certification and badge (I got mine the same day). Two things you can add alongside the projects you’ve worked on.

If there is something I missed, feel free to reach out to me on any of my socials below. And with that Peace out!