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

Input arrays have different dimension (features vector) #2

Open
NLIstudent opened this issue Jul 7, 2020 · 0 comments
Open

Input arrays have different dimension (features vector) #2

NLIstudent opened this issue Jul 7, 2020 · 0 comments

Comments

@NLIstudent
Copy link

Hi I am trying to implement the code..
Since I do not have access to MedNLI, I only used SNLI and MNLI data.
When executing the prepare_feature.py code, I get an error message when all features are concatenated. "All the input arrays must have the same dimensions".
I printed the shapes of each converted features array and the one created in "add_weighted_word_ngram_overlap_feature" looks odd.
Does anyone have an idea why the second dimension is not displayed and how I can fix the problem?

WhatsApp Image 2020-07-06 at 17 42 56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@NLIstudent