Have a question? Connect with the community at the TensorFlow Forum Visit Forum


Retrieves a dict mapping words to their index in the IMDB dataset.

path where to cache the data (relative to ~/.keras/dataset).

The word index dictionary. Keys are word strings, values are their index.


# Retrieve the training sequences.
(x_train, _), _ = keras.datasets.imdb.load_data()
# Retrieve the word index file mapping words to indices
word_index = keras.datasets.imdb.get_word_index()
# Reverse the word index to obtain a dict mapping indices to words
inverted_word_index = dict((i, word) for (word, i) in word_index.items())
# Decode the first sequence in the dataset
decoded_sequence = " ".join(inverted_word_index[i] for i in x_train[0])