Closed StarWang closed 4 years ago
Two general comments: 1) in either the description or readme file update the latest model structure (can use the new feature Xiaowei added last time that dumps the structure to a txt file; 2) can you check if run_ detext_multitask.sh works on multitask test data (not the sparse wide features test data)?
Two general comments: 1) in either the description or readme file update the latest model structure (can use the new feature Xiaowei added last time that dumps the structure to a txt file; 2) can you check if run_ detext_multitask.sh works on multitask test data (not the sparse wide features test data)?
@zhoutong-fu Thanks for the review! I've updated the readme file and tested that run_detext_multitask.sh runs successfully
Description
Currently DeText's design for sparse feature has simple modeling power for sparse features.
This PR resolves the above limitation on sparse feature by
More specifically, the model architecture changes from
to
Type of change
List all changes
Please list all changes in the commit.
Testing
Successfully run run_detext.sh for data including wide_sp_val and sp_emb_size=10
Successfully run run_detext_multitask.sh for data
Unit test for sparse_emb_model when sp_emb_size is 1 and > 1
Checklist
[ ] My code follows the style guidelines of this project
[ ] I have performed a self-review of my own code
[ ] I have commented my code, particularly in hard-to-understand areas
[ ] I have made corresponding changes to the documentation
[ ] My changes generate no new warnings
[ ] I have added tests that prove my fix is effective or that my feature works
[ ] New and existing unit tests pass locally with my changes
[ ] Any dependent changes have been merged and published in downstream modules