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

Kim CNN OOP Refactoring #124

Merged
merged 10 commits into from Jul 3, 2018
Merged

Kim CNN OOP Refactoring #124

merged 10 commits into from Jul 3, 2018

Conversation

tuzhucheng
Copy link
Member

Refactor Kim CNN to use OOP (similar to MP-CNN and VDPWI).

Trainer and evaluator are moved to their own classes. The core training algorithm remains unchanged, it is just structured differently.

@tuzhucheng tuzhucheng mentioned this pull request Jun 10, 2018
Closed
Impavidity
Impavidity approved these changes Jun 10, 2018
View reviewed changes
Copy link
Member

@Impavidity Impavidity left a comment

Choose a reason for hiding this comment

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

LGTM

@tuzhucheng
Copy link
Member Author

Updated README with SST-1 accuracy after hyperparameter tuning per @Impavidity's request.

Test Accuracy on SST-1 rand static non-static multichannel
Paper 45.0 45.5 48.0 47.4
PyTorch using above configs 41.5 44.7 47.4 47.5

With the exception of rand, other modes can get within 1% (absolute) accuracy.

@tuzhucheng tuzhucheng merged commit 8563ad5 into castorini:master Jul 3, 2018
@tuzhucheng tuzhucheng deleted the kim-cnn-michael-refactor branch July 3, 2018 20:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@daemon daemon daemon approved these changes

@Impavidity Impavidity Impavidity approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@tuzhucheng @daemon @Impavidity