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 issue #838 #895

Merged
merged 3 commits into from
Sep 27, 2016
Merged

Fixed issue #838 #895

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
15924cd
Fixed issue #838
markroxor Sep 27, 2016
e04316e
Fixed issue #838
markroxor Sep 27, 2016
8036e2e
Fixed issue #838
markroxor Sep 27, 2016
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
11 changes: 9 additions & 2 deletions gensim/models/word2vec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,7 +273,14 @@ def train_sg_pair(model, word, context_index, alpha, learn_vectors=True, learn_h
l1 += neu1e * lock_factor # learn input -> hidden (mutates model.syn0[word2.index], if that is l1)
return neu1e


def sigmoid(p):
if p > 0:
return 1. / (1. + exp(-p))
elif p <= 0:
exp(p) / (1 + exp(p))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should it say return?

Copy link
Contributor Author

@markroxor markroxor Sep 27, 2016 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That's embarrassing, forgot to return in all the haste. Fixing this PR.

else:
Copy link
Owner

@piskvorky piskvorky Oct 30, 2016 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is this entire if for?

The logic seems obscure (why branch at all? needs at least a comment) and weird (what is the else for?). @tmylk

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@markroxor Please remove else and add comment explaining #838

Copy link
Owner

@piskvorky piskvorky Nov 1, 2016 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I suggest replacing the whole function with scipy.special.expit. Should be faster too (C code).

raise ValueError

def train_cbow_pair(model, word, input_word_indices, l1, alpha, learn_vectors=True, learn_hidden=True):
neu1e = zeros(l1.shape)

Expand All @@ -293,7 +300,7 @@ def train_cbow_pair(model, word, input_word_indices, l1, alpha, learn_vectors=Tr
if w != word.index:
word_indices.append(w)
l2b = model.syn1neg[word_indices] # 2d matrix, k+1 x layer1_size
fb = 1. / (1. + exp(-dot(l1, l2b.T))) # propagate hidden -> output
fb = sigmoid(dot(l1, l2b.T)) # propagate hidden -> output
gb = (model.neg_labels - fb) * alpha # vector of error gradients multiplied by the learning rate
if learn_hidden:
model.syn1neg[word_indices] += outer(gb, l1) # learn hidden -> output
Expand Down