Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix linear decay for learning rate in Doc2Vec.infer_vector. Fix #2061 #2063

Merged
merged 2 commits into from
Jun 20, 2018
+3 −1
Merged

Fix linear decay for learning rate in Doc2Vec.infer_vector. Fix #2061 #2063

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e1e52be
Linear decay for learning rate in infer_vector
umangv May 25, 2018
433d7b7
remove whitespace
umangv May 25, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion gensim/models/doc2vec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -546,6 +546,8 @@ def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5):
if not self.sg:
neu1 = matutils.zeros_aligned(self.trainables.layer1_size, dtype=REAL)

alpha_delta = (alpha - min_alpha) / (steps - 1)

for i in range(steps):
if self.sg:
train_document_dbow(
Expand All @@ -562,7 +564,7 @@ def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5):
self, doc_words, doctag_indexes, alpha, work, neu1,
learn_words=False, learn_hidden=False, doctag_vectors=doctag_vectors, doctag_locks=doctag_locks
)
alpha = ((alpha - min_alpha) / (steps - i)) + min_alpha
alpha -= alpha_delta

return doctag_vectors[0]

Expand Down