As currently written, the one-hot encoding step leaves the user with boolean dummy values that cause errors later in the tutorial as presently written, when passing the np.array() argument to Normalization.adapt().  The values need to be cast to a numerical type (e.g., int) either at the one-hot encoding step or the adapt() step.

Change the verbiage slightly to include
reference to the Tensor docs and note
the nature of the object needing uniform
data types.