[C5][W1] [A3] Missleading comment

Course Q&A Deep Learning Specialization Sequence Models
1

In the UNQ_C3 function,
this comment is missleading :

# Step 3: Convert indices to one-hot vectors, the shape of the results should be (Ty, n_values)

There is no conversion to one hot vectors is required for the “to_categorical”.

why such conversion is required ?

2

The Keras to_categorical() function converts a vector of integers into a matrix of logical values.

3

Yes but the comment would give you indication that you have to use tf.one_hot before calling the “to_categorical”