diff options
Diffstat (limited to 'tensorflow/examples/tutorials/word2vec/word2vec_basic.py')
| -rw-r--r-- | tensorflow/examples/tutorials/word2vec/word2vec_basic.py | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/tensorflow/examples/tutorials/word2vec/word2vec_basic.py b/tensorflow/examples/tutorials/word2vec/word2vec_basic.py index 25800c109e..f54a7c37a1 100644 --- a/tensorflow/examples/tutorials/word2vec/word2vec_basic.py +++ b/tensorflow/examples/tutorials/word2vec/word2vec_basic.py @@ -62,7 +62,7 @@ print('Data size', len(words)) vocabulary_size = 50000 -def build_dataset(words): +def build_dataset(words, vocabulary_size): count = [['UNK', -1]] count.extend(collections.Counter(words).most_common(vocabulary_size - 1)) dictionary = dict() @@ -81,7 +81,7 @@ def build_dataset(words): reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys())) return data, count, dictionary, reverse_dictionary -data, count, dictionary, reverse_dictionary = build_dataset(words) +data, count, dictionary, reverse_dictionary = build_dataset(words, vocabulary_size) del words # Hint to reduce memory. print('Most common words (+UNK)', count[:5]) print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]]) @@ -181,7 +181,7 @@ with graph.as_default(): valid_embeddings, normalized_embeddings, transpose_b=True) # Add variable initializer. - init = tf.initialize_all_variables() + init = tf.global_variables_initializer() # Step 5: Begin training. num_steps = 100001 |