Part 1: Exploring the to_categorical() function

Did you know that in real-world problems, the vocabulary size can grow very large (e.g. more than hundred thousand)?

This exercise is broken into two parts and you will learn the importance of setting the num_classes argument of the to_categorical() function. In part 1, you will implement the function compute_onehot_length() that generates one-hot vectors for a given list of words and computes the length of those vectors.

The to_categorical() function has already been imported.

Deze oefening maakt deel uit van de cursus

Machine Translation with Keras

Cursus bekijken

Oefeninstructies

Create word IDs by using words and word2index in compute_onehot_length().
Create onehot vectors using the to_categorical() function using the word IDs.
Return the length of a single onehot vector using the <array>.shape syntax.
Compute and print the length of onehot vectors using compute_onehot_length() for the list of words He, drank, milk.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

def compute_onehot_length(words, word2index):
  # Create word IDs for words
  word_ids = [____[w] for w in ____]
  # Convert word IDs to onehot vectors
  onehot = ____(____)
  # Return the length of a single one-hot vector
  return onehot.____[1]

word2index = {"He":0, "drank": 1, "milk": 2}
# Compute and print onehot length of a list of words
print(____([____,____,____], ____))

Code bewerken en uitvoeren