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

Jump to bottom

Fixed bug in loss computation for Word2Vec with hierarchical softmax #3397

Merged
merged 2 commits into from
Nov 3, 2022
Merged

Fixed bug in loss computation for Word2Vec with hierarchical softmax #3397

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f3ae9aa
fixed loss computation for sg, hs
TalIfargan Oct 31, 2022
7c3e6d0
fixed loss computation for cbow, hs
TalIfargan Nov 1, 2022
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: 2 additions & 2 deletions gensim/models/word2vec_inner.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,7 @@ cdef void w2v_fast_sentence_sg_hs(

if _compute_loss == 1:
sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1
lprob = -1*sgn*f_dot
lprob = sgn*f_dot
if lprob <= -MAX_EXP or lprob >= MAX_EXP:
continue
lprob = LOG_TABLE[<int>((lprob + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))]
Expand Down Expand Up @@ -326,7 +326,7 @@ cdef void w2v_fast_sentence_cbow_hs(

if _compute_loss == 1:
sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1
lprob = -1*sgn*f_dot
lprob = sgn*f_dot
if lprob <= -MAX_EXP or lprob >= MAX_EXP:
continue
lprob = LOG_TABLE[<int>((lprob + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))]
Expand Down