Share this page!

Santiago Profile picture
Twitter logo
27 Mar, 6 tweets, 2 min read
This is the one.
Yes, this is the edition updated for TensorFlow 2.

Here is a GitHub repo for this book: github.com/ageron/handson…

I promise you'll have no issues with the style and code quality of this book.

It's primarily a hands-on book, so it's not a theoretical book.

That being said, I feel it strikes the right balance between enough theory and practice.

These are the main libraries I use, for sure. There are others as well, but the core is right here.

And no, I don't usually write anything from scratch unless I'm trying to learn or teach specific concepts.

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Santiago

Santiago Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @svpino

Santiago Profile picture
29 Mar
I've talked about Transfer Learning before.

In summary: you can reuse the knowledge from a different model to kick-start your new model.

Practically, this is how I make transfer learning happen: 🧵👇
First, I pick the model architecture I'll be transferring from.

There are hundreds of pre-trained models for TensorFlow (Check TensorFlow Hub.)

I spend most of my time working with images, and my go-to is usually ResNet with ImageNet weights.

↓ 2/10 Image
I instantiate the model without its top layer and load the pre-trained weights into it.

To make sure I don't destroy those weights during training, I freeze those weights. Frozen weights won't change.

↓ 3/10
Read 10 tweets
Santiago Profile picture
27 Mar
$5 for the next 2 hours. Back to $15 after that.
$0 if you don't like it.

If you don't want it but still want to support my work, like/retweet this message. Thanks!

gumroad.com/l/kBjbC/rfgnxf4
Thanks for the support, everyone!

This worked.

1 more hour to go.
10 more copies and price goes back.
Read 8 tweets
Santiago Profile picture
27 Mar
The perfect way to get into machine learning is to find an algorithm that improves your work right away without much drama.

For software developers, KNN (K-Nearest Neighbors) is a perfect introduction:

▫️ Surprisingly familiar
▫️ Powerful enough

🧵👇
I also like Decision Trees for software developers, but if you did that already, look into KNN.

Here is the summary you need to know: KNN is like a fancy search algorithm that will help you do cool things.

2/6
Here are some of the things that you could solve using KNN:

1. If you have a dataset with missing values, you can use KNN to find a good value for them.

2. You can build a simple recommendation system to promote related products in your store using KNN.

3/6
Read 7 tweets
Santiago Profile picture
27 Mar
Why should you consider machine learning?

▫️ Better career opportunities
▫️ Pays really well
▫️ Rapid growth
▫️ It's shaping the future
▫️ Creativity over repetition

Most importantly, it gives us access to solve problems that we wouldn't be able to crack without.
You might not have focused on it yet, but it's not as far from you as you may think.

Here is my recommendation: start reading about it a little bit. You don't have to make any world-rocking changes, just inform yourself better and see what happens.

This depends on your country and the opportunities that exist around you. That being said, conventional development jobs will continue to be more popular.

But every day, there will be more machine learning jobs. The demand will continue increasing.

Read 5 tweets
Santiago Profile picture
26 Mar
I've been talking about machine learning for a while now.

It has taken me some time to understand who is my audience, and—more importantly—, who do I want to speak to.

1/5
I want my content to be driven by what excites me. That's the only way I can ensure I'll stay engaged and the content will have a high quality.

I listen to what people want to shape my ideas but always prioritize what I want to say.

2/5
Here is the persona that I want to talk to:

"You are a software developer interested in incorporating machine learning into your tool set. You might be starting from scratch or be on your way, but you aren't an expert yet ... →

3/5
Read 5 tweets
Santiago Profile picture
25 Mar
A summary of the setup I use for work and how I use each one of these:

▫️ Google Colab PRO
▫️ @awscloud's SageMaker
▫️ Mac Pro running @code

Here are the details: 🧵👇
I always start new things with Google Colab.

Opening Colab is fast, and I can go from an idea to a running script in no time.

I can share the notebook and open it anywhere without worrying about version control systems.

2/9
Any new experiments go into Colab. Whenever I need to test something, I do it in Colab.

Paying for the PRO version is a no-brainer for me:

▫️ Faster GPUs
▫️ More RAM
▫️ More Disk
▫️ Longer runtime

3/9
Read 9 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

Like this author's thread?

Get emails when @svpino has new unrolls!

Check out other threads from @svpino!

Read all threads by @svpino