lunny/keras
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix off by one error in WE example script

Browse Source 
Tokenizer returns sequence values in the range of [0, nb_words). In this
example, MAX_NB_WORDS is 20000 and the data's min value is 19999. There
is no need to use 'nb_words + 1'.
This commit is contained in:
Minkoo Seo 2017-02-07 03:53:33 +09:00 committed by François Chollet
parent 4cd3d284e9
commit f1a95869eb
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/pretrained_word_embeddings.py
View File

@ -102,9 +102,9 @@ print('Preparing embedding matrix.')
# prepare embedding matrix
nb_words = min(MAX_NB_WORDS, len(word_index))
embedding_matrix = np.zeros((nb_words + 1, EMBEDDING_DIM))
embedding_matrix = np.zeros((nb_words, EMBEDDING_DIM))
for word, i in word_index.items():
if i > MAX_NB_WORDS:
if i >= MAX_NB_WORDS:
continue
embedding_vector = embeddings_index.get(word)
if embedding_vector is not None:
@ -113,7 +113,7 @@ for word, i in word_index.items():
# load pre-trained word embeddings into an Embedding layer
# note that we set trainable = False so as to keep the embeddings fixed
embedding_layer = Embedding(nb_words + 1,
embedding_layer = Embedding(nb_words,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,