This is not a fancy tutorial. It is the guide I wish I had when I was getting started.

View these in the order provided; don’t try to memorize everything: (You may choose to install TensorFlow now if you haven’t already.) (Stop reading after the model diagram.) (Stop reading once you get to “Examples”.)

About callbacks

You can use the functional API for unique architechures

At this point you should have a good understanding. Google things and refer to the documentation as needed.

Keras in R

I prefer using Keras in Python, but you can also run it from R.
The R Keras installation can be a little unfriendly, so here are some tips:

To save time, avoid issues by updating these packages first.
install.packages(c("ps", "Rcpp", "digest", "processx", "devtools"))

Install TensorFlow.
tensorflow::install_tensorflow() Include the argument gpu=TRUE if you want GPU processing.

Verify TF installation.

Install Keras.
If you update other packages when prompted and one of them fails, perform install.packages('package_name') separately, then run devtools::install_github("rstudio/keras") again.

Allow installation of Miniconda unless you insist otherwise.

If you are familiar with R, the Keras usage will be easy to understand:


This, along with its own references, helped me when installing Keras in R and some of these notes come from them: