This is an automated email from the ASF dual-hosted git repository. joern pushed a commit to branch namecat_shuffle in repository https://gitbox.apache.org/repos/asf/opennlp-sandbox.git
commit 4d63911591c268e1ccabd0bd40390d6fdbd726d8 Author: Jörn Kottmann <[email protected]> AuthorDate: Wed Apr 3 10:38:10 2019 +0200 Shuffle the training samples for each epoch in namecat --- tf-ner-poc/src/main/python/namecat/namecat.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tf-ner-poc/src/main/python/namecat/namecat.py b/tf-ner-poc/src/main/python/namecat/namecat.py index 86822c0..cc3f28a 100644 --- a/tf-ner-poc/src/main/python/namecat/namecat.py +++ b/tf-ner-poc/src/main/python/namecat/namecat.py @@ -169,7 +169,11 @@ def main(): acc_train = [] batch_indexes = list(range(floor(len(names_train) / batch_size))) - random.Random(epoch).shuffle(batch_indexes) + + # Shuffle the data + combined = list(zip(names_train, labels_train)) + random.shuffle(combined) + names_train[:], labels_train[:] = zip(*combined) for batch_index in batch_indexes: label_train_batch, name_train_batch, name_train_length = \
