-
Notifications
You must be signed in to change notification settings - Fork 812
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
Add Sentencepiece binding to torchtext, plus example to build torchtext dataset with sentencepiece #597
Commits on Aug 26, 2019
-
Add sentencepiece dependency to torchtext package
Guanheng Zhang committedAug 26, 2019 Configuration menu - View commit details
-
Copy full SHA for 1be09e2 - Browse repository at this point
Copy the full SHA 1be09e2View commit details -
Add generate_sentencepiece_tokenizer_model
Guanheng Zhang committedAug 26, 2019 Configuration menu - View commit details
-
Copy full SHA for 160930f - Browse repository at this point
Copy the full SHA 160930fView commit details
Commits on Aug 29, 2019
-
Guanheng Zhang committed
Aug 29, 2019 Configuration menu - View commit details
-
Copy full SHA for 3abe2a8 - Browse repository at this point
Copy the full SHA 3abe2a8View commit details
Commits on Sep 3, 2019
-
Test on YelpFullReview with 20k vocab. Same results as fastText.
Guanheng Zhang committedSep 3, 2019 Configuration menu - View commit details
-
Copy full SHA for 4e230e9 - Browse repository at this point
Copy the full SHA 4e230e9View commit details
Commits on Sep 9, 2019
-
Guanheng Zhang committed
Sep 9, 2019 Configuration menu - View commit details
-
Copy full SHA for 030fc4e - Browse repository at this point
Copy the full SHA 030fc4eView commit details -
Reset text_classification dataset.
Guanheng Zhang committedSep 9, 2019 Configuration menu - View commit details
-
Copy full SHA for 2a219b0 - Browse repository at this point
Copy the full SHA 2a219b0View commit details -
Merge branch 'sentence_piece' into example_spm
Guanheng Zhang committedSep 9, 2019 Configuration menu - View commit details
-
Copy full SHA for 853edbc - Browse repository at this point
Copy the full SHA 853edbcView commit details -
Train a model if spm is not provided.
Guanheng Zhang committedSep 9, 2019 Configuration menu - View commit details
-
Copy full SHA for 69f2ae0 - Browse repository at this point
Copy the full SHA 69f2ae0View commit details -
Allow to call setup_datasets() func
Guanheng Zhang committedSep 9, 2019 Configuration menu - View commit details
-
Copy full SHA for 7bf8146 - Browse repository at this point
Copy the full SHA 7bf8146View commit details
Commits on Sep 10, 2019
-
Guanheng Zhang committed
Sep 10, 2019 Configuration menu - View commit details
-
Copy full SHA for 5f4ee68 - Browse repository at this point
Copy the full SHA 5f4ee68View commit details
Commits on Sep 11, 2019
-
Guanheng Zhang committed
Sep 11, 2019 Configuration menu - View commit details
-
Copy full SHA for c41eea3 - Browse repository at this point
Copy the full SHA c41eea3View commit details -
Guanheng Zhang committed
Sep 11, 2019 Configuration menu - View commit details
-
Copy full SHA for eb6fa30 - Browse repository at this point
Copy the full SHA eb6fa30View commit details -
Guanheng Zhang committed
Sep 11, 2019 Configuration menu - View commit details
-
Copy full SHA for 457cd39 - Browse repository at this point
Copy the full SHA 457cd39View commit details -
Guanheng Zhang committed
Sep 11, 2019 Configuration menu - View commit details
-
Copy full SHA for c883dd1 - Browse repository at this point
Copy the full SHA c883dd1View commit details
Commits on Sep 12, 2019
-
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for 943538b - Browse repository at this point
Copy the full SHA 943538bView commit details -
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for d6eae59 - Browse repository at this point
Copy the full SHA d6eae59View commit details -
Update the test for get_tokenizer
Guanheng Zhang committedSep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for 43b78a3 - Browse repository at this point
Copy the full SHA 43b78a3View commit details -
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for 98470a0 - Browse repository at this point
Copy the full SHA 98470a0View commit details -
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for 82ecd71 - Browse repository at this point
Copy the full SHA 82ecd71View commit details -
Add test to cover generate_sp_tokenizer() function.
Guanheng Zhang committedSep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for 535be98 - Browse repository at this point
Copy the full SHA 535be98View commit details -
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for c787099 - Browse repository at this point
Copy the full SHA c787099View commit details -
Add spm_data_generator() func.
Guanheng Zhang committedSep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for f0da161 - Browse repository at this point
Copy the full SHA f0da161View commit details -
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for 1d40431 - Browse repository at this point
Copy the full SHA 1d40431View commit details -
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for 251ac60 - Browse repository at this point
Copy the full SHA 251ac60View commit details -
Add test to cover spm_data_generator
Guanheng Zhang committedSep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for a2b628c - Browse repository at this point
Copy the full SHA a2b628cView commit details -
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for 80b0eec - Browse repository at this point
Copy the full SHA 80b0eecView commit details -
Guanheng Zhang committed
Sep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for c375ae3 - Browse repository at this point
Copy the full SHA c375ae3View commit details -
skip test_get_tokenizer_sentencepiece in python2 envir.
Guanheng Zhang committedSep 12, 2019 Configuration menu - View commit details
-
Copy full SHA for d2d5438 - Browse repository at this point
Copy the full SHA d2d5438View commit details
Commits on Sep 13, 2019
-
Guanheng Zhang committed
Sep 13, 2019 Configuration menu - View commit details
-
Copy full SHA for 4959eb6 - Browse repository at this point
Copy the full SHA 4959eb6View commit details -
Guanheng Zhang committed
Sep 13, 2019 Configuration menu - View commit details
-
Copy full SHA for f9d5314 - Browse repository at this point
Copy the full SHA f9d5314View commit details -
Guanheng Zhang committed
Sep 13, 2019 Configuration menu - View commit details
-
Copy full SHA for 75015ed - Browse repository at this point
Copy the full SHA 75015edView commit details -
Guanheng Zhang committed
Sep 13, 2019 Configuration menu - View commit details
-
Copy full SHA for 80fc33e - Browse repository at this point
Copy the full SHA 80fc33eView commit details -
byte string in Python2 and Unicode string in Python3 respectively
Guanheng Zhang committedSep 13, 2019 Configuration menu - View commit details
-
Copy full SHA for 5fd36de - Browse repository at this point
Copy the full SHA 5fd36deView commit details
Commits on Sep 18, 2019
-
Revise based on reviewers' feedback.
Guanheng Zhang committedSep 18, 2019 Configuration menu - View commit details
-
Copy full SHA for 7505649 - Browse repository at this point
Copy the full SHA 7505649View commit details -
Guanheng Zhang committed
Sep 18, 2019 Configuration menu - View commit details
-
Copy full SHA for 556a3bc - Browse repository at this point
Copy the full SHA 556a3bcView commit details -
Add test to cover SentencePieceTransform.
Guanheng Zhang committedSep 18, 2019 Configuration menu - View commit details
-
Copy full SHA for 3f48f2b - Browse repository at this point
Copy the full SHA 3f48f2bView commit details -
Remove sentencepiece from get_tokenizer.
Guanheng Zhang committedSep 18, 2019 Configuration menu - View commit details
-
Copy full SHA for b7d12ed - Browse repository at this point
Copy the full SHA b7d12edView commit details -
Guanheng Zhang committed
Sep 18, 2019 Configuration menu - View commit details
-
Copy full SHA for 2436af0 - Browse repository at this point
Copy the full SHA 2436af0View commit details
Commits on Sep 19, 2019
-
Guanheng Zhang committed
Sep 19, 2019 Configuration menu - View commit details
-
Copy full SHA for d5e159d - Browse repository at this point
Copy the full SHA d5e159dView commit details -
Guanheng Zhang committed
Sep 19, 2019 Configuration menu - View commit details
-
Copy full SHA for c37b500 - Browse repository at this point
Copy the full SHA c37b500View commit details -
Guanheng Zhang committed
Sep 19, 2019 Configuration menu - View commit details
-
Copy full SHA for f4e4f15 - Browse repository at this point
Copy the full SHA f4e4f15View commit details -
Guanheng Zhang committed
Sep 19, 2019 Configuration menu - View commit details
-
Copy full SHA for ac2a8ee - Browse repository at this point
Copy the full SHA ac2a8eeView commit details -
Add docs for SentencePieceTransform.
Guanheng Zhang committedSep 19, 2019 Configuration menu - View commit details
-
Copy full SHA for 2f859f4 - Browse repository at this point
Copy the full SHA 2f859f4View commit details -
Guanheng Zhang committed
Sep 19, 2019 Configuration menu - View commit details
-
Copy full SHA for 7fea165 - Browse repository at this point
Copy the full SHA 7fea165View commit details
Commits on Sep 20, 2019
-
Add sentencepiece functionals.
Guanheng Zhang committedSep 20, 2019 Configuration menu - View commit details
-
Copy full SHA for 5d84383 - Browse repository at this point
Copy the full SHA 5d84383View commit details -
Guanheng Zhang committed
Sep 20, 2019 Configuration menu - View commit details
-
Copy full SHA for 50c5896 - Browse repository at this point
Copy the full SHA 50c5896View commit details -
Merge remote-tracking branch 'upstream/master' into example_spm
Guanheng Zhang committedSep 20, 2019 Configuration menu - View commit details
-
Copy full SHA for 7ffba4a - Browse repository at this point
Copy the full SHA 7ffba4aView commit details -
Remove spm_data_generator docs.
Guanheng Zhang committedSep 20, 2019 Configuration menu - View commit details
-
Copy full SHA for 1fbda39 - Browse repository at this point
Copy the full SHA 1fbda39View commit details
Commits on Sep 23, 2019
-
move generate_sp_tokenizer to functional.py.
Guanheng Zhang committedSep 23, 2019 Configuration menu - View commit details
-
Copy full SHA for 3eb82e6 - Browse repository at this point
Copy the full SHA 3eb82e6View commit details -
Fix the docstring of lr-garmma.
Guanheng Zhang committedSep 23, 2019 Configuration menu - View commit details
-
Copy full SHA for 5812ce6 - Browse repository at this point
Copy the full SHA 5812ce6View commit details -
Guanheng Zhang committed
Sep 23, 2019 Configuration menu - View commit details
-
Copy full SHA for f84a933 - Browse repository at this point
Copy the full SHA f84a933View commit details
Commits on Sep 24, 2019
-
Merge remote-tracking branch 'upstream/master' into example_spm
Guanheng Zhang committedSep 24, 2019 Configuration menu - View commit details
-
Copy full SHA for 8402863 - Browse repository at this point
Copy the full SHA 8402863View commit details -
Guanheng Zhang committed
Sep 24, 2019 Configuration menu - View commit details
-
Copy full SHA for 70f09f9 - Browse repository at this point
Copy the full SHA 70f09f9View commit details -
Guanheng Zhang committed
Sep 24, 2019 Configuration menu - View commit details
-
Copy full SHA for 4d6881b - Browse repository at this point
Copy the full SHA 4d6881bView commit details -
Guanheng Zhang committed
Sep 24, 2019 Configuration menu - View commit details
-
Copy full SHA for 59752a7 - Browse repository at this point
Copy the full SHA 59752a7View commit details -
Guanheng Zhang committed
Sep 24, 2019 Configuration menu - View commit details
-
Copy full SHA for 0e9844c - Browse repository at this point
Copy the full SHA 0e9844cView commit details -
Guanheng Zhang committed
Sep 24, 2019 Configuration menu - View commit details
-
Copy full SHA for 3e2d8b8 - Browse repository at this point
Copy the full SHA 3e2d8b8View commit details -
Merge text_classification and sentencepiece examples.
Guanheng Zhang committedSep 24, 2019 Configuration menu - View commit details
-
Copy full SHA for 6215f95 - Browse repository at this point
Copy the full SHA 6215f95View commit details
Commits on Sep 25, 2019
-
Guanheng Zhang committed
Sep 25, 2019 Configuration menu - View commit details
-
Copy full SHA for 6740b9d - Browse repository at this point
Copy the full SHA 6740b9dView commit details -
Merge sentencepiece example to text_classification.
Guanheng Zhang committedSep 25, 2019 Configuration menu - View commit details
-
Copy full SHA for 0d9162a - Browse repository at this point
Copy the full SHA 0d9162aView commit details -
Guanheng Zhang committed
Sep 25, 2019 Configuration menu - View commit details
-
Copy full SHA for 803f24f - Browse repository at this point
Copy the full SHA 803f24fView commit details -
Guanheng Zhang committed
Sep 25, 2019 Configuration menu - View commit details
-
Copy full SHA for ce8b558 - Browse repository at this point
Copy the full SHA ce8b558View commit details -
Guanheng Zhang committed
Sep 25, 2019 Configuration menu - View commit details
-
Copy full SHA for 200a4e4 - Browse repository at this point
Copy the full SHA 200a4e4View commit details
Commits on Sep 26, 2019
-
Guanheng Zhang committed
Sep 26, 2019 Configuration menu - View commit details
-
Copy full SHA for 8aabcdd - Browse repository at this point
Copy the full SHA 8aabcddView commit details -
Guanheng Zhang committed
Sep 26, 2019 Configuration menu - View commit details
-
Copy full SHA for b93149f - Browse repository at this point
Copy the full SHA b93149fView commit details -
Move transforms to functional.
Guanheng Zhang committedSep 26, 2019 Configuration menu - View commit details
-
Copy full SHA for 08dd450 - Browse repository at this point
Copy the full SHA 08dd450View commit details -
Guanheng Zhang committed
Sep 26, 2019 Configuration menu - View commit details
-
Copy full SHA for 6a69800 - Browse repository at this point
Copy the full SHA 6a69800View commit details -
Change to --sp-vocab-size example train.py.
Guanheng Zhang committedSep 26, 2019 Configuration menu - View commit details
-
Copy full SHA for f01e201 - Browse repository at this point
Copy the full SHA f01e201View commit details -
Guanheng Zhang committed
Sep 26, 2019 Configuration menu - View commit details
-
Copy full SHA for 20534ea - Browse repository at this point
Copy the full SHA 20534eaView commit details -
Guanheng Zhang committed
Sep 26, 2019 Configuration menu - View commit details
-
Copy full SHA for 7136d8c - Browse repository at this point
Copy the full SHA 7136d8cView commit details -
Guanheng Zhang committed
Sep 26, 2019 Configuration menu - View commit details
-
Copy full SHA for 76f8d8c - Browse repository at this point
Copy the full SHA 76f8d8cView commit details