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.

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

bug fix in get_sentiment function #206

Merged
merged 1 commit into from
Apr 23, 2020
Merged

Conversation

tejasvaidhyadev
Copy link
Member

@tejasvaidhyadev tejasvaidhyadev commented Apr 16, 2020

As mentioned #205 and #187
Bug fixed in sentiment function
In file sentiment_weights we are having having 32×5000 matrices with index-1 is default pad token embedding
But here
in src/sentiment.jl
if ele in keys(rwi) && rwi[ele] <= ( size(weight[:embedding_1]["embedding_1"]["embeddings:0"])[2] ) # there are only 5000 unique embeddings -
we are allowing 5000 unique embedding excluding padding which implies 5001 unique embedding but we have only 32×5000 weight.
I am not sure about training process may be we are training on only first 5000 element with padding token then replacing above line will work.

@tejasvaidhyadev tejasvaidhyadev changed the title bug fix in get sentiment function bug fix in get_sentiment function Apr 16, 2020
@tejasvaidhyadev
Copy link
Member Author

@aviks
you can review the given PR

@aviks aviks merged commit a959025 into JuliaText:master Apr 23, 2020
@tejasvaidhyadev tejasvaidhyadev deleted the bug_fix branch April 23, 2020 13:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants