Reusing Pretrained Categorical Embeddings (lesson 7)

I’m confused on the process of how categorical embeddings from a NN can be concatenated with continuous variables and used in a Random Forest. Specifically embedding shape (rows) do not fit that of the original input (e.g. learn.model.embeds.parameters(). , thus I’m unclear how these can be concatenated to form the X for a new model such as a RandomForest.

Please forgive my ignorance, as although this topic was raised a few times, I cannot find an explanation of the steps with fastai.

1 Like

This same question was asked (and answered with a notebook) < 24 hrs ago. Please do a thorough search so we do not have multiple topics on the same thing (or ask on one of those threads!)

Using embedding from the Neural Network in Random Forests