Commit Graph
105 Commits
Author SHA1 Message Date
Jimmy Lin 0c185a8bda Update README.md 2018-05-27 07:38:03 -04:00
Jimmy Lin bc74ae6531 Update README.md 2018-05-27 07:07:35 -04:00
Jimmy Lin c59739488c Update README.md 2018-05-27 07:06:32 -04:00
Jimmy Lin 97a76495fd Update requirements.txt (#116) 2018-05-26 22:53:26 -04:00
Jimmy Lin 3b426c1c25 Update README.md (#117) 2018-05-26 22:05:54 -04:00
Jimmy Lin bc58fc7607 Update README.md (#115) 2018-05-26 18:37:24 -04:00
Michael Tu 5bf33bf8ea Update README to use Castor-models and Instructions for Internal Users (#113)
* Update instructions to use Castor-models
* Consolidate requirements.txt
* Refine README with convenience scripts
* Update internal instructions
* MP-CNN working dir minor edit
2018-05-25 18:14:10 -04:00
Ralph Tang 62f8abec7f Add README (#110)
* Make *QA/MSRVID work with VDPWI

* Add README
2018-05-25 11:52:25 -04:00
Michael Tu ef05240819 Update MP-CNN Doc with Pre-Trained Models (#111)
* Delete outdated troubleshooting section

* QAEvalutor bugfix

* Add instructions for pre-trained models
2018-05-25 11:51:19 -04:00
Ralph Tang 494ce36575 Refactor VDPWI to use common API (#109) 2018-05-25 01:30:53 -04:00
Michael Tu 0c3a91c443 Check in MP-CNN Lite Model (#108)
* Add MP-CNN Lite model

* MP-CNN Lite bug fixes
2018-05-25 00:15:50 -04:00
Michael Tu d7a631b0a9 MP-CNN with Bugs Fixed and PyTorch v0.4 (#107)
* Refactor datasets

* Update evaluators

* Update trainers

* Update main and MP-CNN model

* Add serialization util

* Fix bugs

* Refactoring for NCE to use new parent class
2018-05-24 23:42:13 -04:00
Ralph Tang fbd8629ca2 Move MPCNN API to common module (#105) 2018-05-24 18:02:37 -04:00
Jimmy Lin 4ece3c7ade Merge pull request #104 from daemon/vdpwi
Merge in existing VDPWI code
2018-05-23 19:13:49 -04:00
Ralph Tang 76a99398ac Remove extraneous files from VDPWI 2018-05-23 17:55:34 -04:00
Ralph Tang bb5cf71f9c Merge remote-tracking branch 'vdpwi/master' 2018-05-23 17:42:53 -04:00
Jimmy Lin cc53e60098 Update README.md 2018-05-23 16:34:33 -04:00
Jimmy Lin 344248449e Update README.md 2018-05-23 16:26:39 -04:00
Michael Tu f7a0167b81 Migrate to from GitHub castorini/data to uWaterloo Castor-data (#103)
* Refactor main README
* Update Anserini Dependency docs
* Update idf baseline and Kim CNN docs to use Castor-data
* Update remaining READMEs to reference Castor-data
* Change default path from data to Castor-data
* Fix wrong order of embeddings path
2018-05-23 16:16:17 -04:00
Ralph Tang 73823fcc32 Make model parallel wrt batch size 2018-02-06 19:49:12 -05:00
Ralph Tang 4b266431ff Add hyperparameter tuning script 2018-02-05 17:57:52 -05:00
Ralph Tang 901ce4d6a4 Add tensorboard visualization 2018-02-05 15:25:59 -05:00
Ralph Tang b06547b36e Fix norm gradient explosion 2018-02-05 02:48:34 -05:00
Ralph Tang a110b03164 Add GPU loop unrolling for SimCube computation 2018-02-04 23:20:22 -05:00
Ralph Tang 28f62623be Workaround PT padding_idx bug 2018-02-04 22:00:55 -05:00
Ralph Tang 5df6123aba Add training code 2018-02-04 21:39:25 -05:00
Ralph Tang 579d187d8e Add VDPWI core models 2018-02-04 16:10:38 -05:00
Ralph Tang e08f85dc09 Fix sigma bug 2018-02-04 14:17:51 -05:00
Ralph Tang 9e2aaf2788 Add preprocessing scripts 2018-02-03 22:54:58 -05:00
Ralph Tang cc7471a595 Initial commit 2018-02-03 00:10:57 -05:00
rosequ ef21aa975f SHARCNET tutorial (#97) 2018-01-24 20:11:26 -05:00
Victor Yang 5fd31a0434 Update path name and README for NCE-SM (#95)
* update nce-sm

* refactor code, update torchtext

* use shared evaluation

* refactor code, use shared data loader

* refactor code

* refactor code

* refactor code according to Michael's great suggestions

* update readme and requirement

* update datasets and readme

* update data loader

* add space between +

* update path name, update readme

* update data loader and dataset name

* refactor code

* update readme
2018-01-24 14:12:37 -05:00
Michael Tu cbd54cb382 Kim CNN README remove torchtext reset (#96) 2018-01-18 10:42:09 -05:00
Victor Yang 51d8e29525 add NCE to MP-CNN (#84)
* update nce-sm

* refactor code, update torchtext

* use shared evaluation

* refactor code, use shared data loader

* refactor code

* refactor code

* refactor code according to Michael's great suggestions

* update readme and requirement

* update datasets and readme

* update data loader

* add space between +

* update refactor code

* add nce-mp

* remove duplicate files

* update readme, refactor code according to mp_cnn and delete duplicate code, follow PEP8 standard

* refactor code, add/delete comments

* import exit from sys
2018-01-03 18:12:57 -05:00
Michael Tu eee160ea41 Use view instead of unsqueeze since ONNX v1.0 doesn't support it (#94) 2017-12-08 15:04:29 -05:00
rosequ 85f35bb994 connected the pipeline (#65) (#93)
* connected the pipeline

* minor changes to api code
2017-12-07 20:04:18 -05:00
rosequ 68e0ef45b2 Util to build w2v pytorch model (#92)
* util to build w2v pytorch model

* added the code to build the .pt model
2017-12-06 11:34:29 -05:00
Michael Tu a363e3d256 Add flag to support onnx (#91) 2017-12-06 09:55:02 -05:00
rosequ 0a3ce7015c Update readme (#90)
* updated readme for easier replication

* updated cd changes

* link change
2017-12-05 21:58:55 -05:00
rosequ 28a198f33c Update bridge (#87) (#89)
* initial commit of the updated bridge

* moved bridge file to the root

* after CR1

* after CR2
2017-12-05 12:23:08 -05:00
rosequ aee1541722 avoids parsing exceptions (#88)
* avoids parsing exceptions

* remove unnecessary print
2017-12-02 10:23:40 -05:00
MeowFei ad69d3abc2 Connected to E2E pipeline (#85)
* added RetrieveSentences.py

* removed index

* connet to E2E pipeline

* updated code

* Some modification

* clean up

* config

* documentation

* added documentation

* update documentation

* update doc

* update doc

* add js

* updated documentation

* changed doc

* changed requirements.txt
2017-11-25 14:39:39 -05:00
Victor Yang 61c8c0e622 update nce-sm (#78)
* update nce-sm

* refactor code, update torchtext

* use shared evaluation

* refactor code, use shared data loader

* refactor code

* refactor code

* refactor code according to Michael's great suggestions

* update readme and requirement

* update datasets and readme

* update data loader

* add space between +
2017-11-09 17:03:43 -05:00
Michael Tu 0722dde06e MP-CNN: Add hyperparameters used to achieve paper perf for WikiQA (#82) 2017-11-08 09:51:04 -05:00
Michael Tu aaff291edb Update Kim CNN SST-1 dataset to use torchtext 0.2.0 (#81) 2017-11-07 21:37:18 -05:00
Michael Tu 2344354cbf MP-CNN: add trainer and evaluator for WikiQA (#80) 2017-11-06 20:37:40 -05:00
Michael Tu 4132874bad Add WikiQA Dataset (#79) 2017-11-04 18:41:32 -04:00
Michael Tu 4470983504 TrecQA for MP-CNN (#77)
* Add TrecQA dataset and modularize MP-CNN infra

* Stylistic improvements

* Fix and warn about trec_eval path issue

* Update README for MP-CNN

* Update incorrect map/mrr

* MP-CNN: address code review comments

* Create common Castor pair Dataset class

* Move map and mrr computation to Castor utils

* Make map mrr utility trec_eval path more general
2017-11-04 18:22:40 -04:00
Michael Tu 09b3a790a2 Use torchtext for MP-CNN (#76)
* Add SICK torchtext Dataset

* SICK dataset - torchtext postprocess into class probs

* Update model, driver, trainer, evaluator for SICK for torchtext

* MP-CNN: Fix bugs that prevent SICK from running on gpu 0

* MP-CNN: make SICK dataset w/ torchtext GPU-agnostic

* MP-CNN: support sparse features / idf overlap with torchtext

* Add MSRVID dataset with torchtext and update MP-CNN code to use it

* MP-CNN: Make torchtext deterministic by setting python random seed

* SICK and MSRVID datasets - add pair id for debug and build test vocab

* MP-CNN: Update readme to address potential module not found error

* MP-CNN: address review comments, can run on cpu
2017-11-01 12:13:30 -04:00
Peng Shi 4dea22b40f Deterministic CNN #45 (#71)
* Deterministic CNN #45

* Describe the data source
2017-10-30 22:23:00 -04:00