Here is the forward method for TabularModel:

We won’t show __init__ here, since it’s not that interesting, but we will look at each line of code in forward in turn. The first line:

and concatenates them into a single tensor:

Then dropout is applied. You can pass embd_p to __init__ to change this value:

They are passed through a batchnorm layer:

and concatenated with the embedding activations, if there were any:

x = torch.cat([x, x_cont], 1) if self.n_emb != 0 else x_cont

Congratulations! Now you know every single piece of the architectures used in the fastai library!