Anybody Have Tidy Examples of Deep Learning Models with keras?

keras
tensorflow

#1

I’m trying to learn how to use keras in R, but I find that most of the code examples I see online aren’t too neatly coded, and that makes it kind of hard for me to grasp. Does anybody know of any examples of using keras in R with a more tidy approach?


Deep Learning in R x Python
#2

Did you go through the examples here? The code is pretty clean and some of examples are fairly advanced.


#3

You will find some examples too in the blog section of @mishabalyasin links
https://tensorflow.rstudio.com/categories/keras.html

Do not hesitate to subscribe to the website for updates. I suggest you this book if you want to go further


#4

Grid Search Tuning of Keras Models


#5

Personally I was a bit disappointed by this book.

The explanation of the concepts is pretty good, but I feel like the code-examples could be far more tidy. Almost every code snippet uses some sort of a for-loop, and some old “base-R” conventions instead of the Tidyverse-versions.


#6

I agree, way too many for-loops. I feel like there have to be cleaner ways to do that

It’s not the worst thing to have to tidy the code myself, but it’s hard when unfamiliar with the purpose of the code.


#7

I think the point was to focus on the basics of the modeling and to keep it as similar to the python book as possible.

Introducing the tidyverse and the applicable packages would be a big and awkward diversion.