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

Textmodel integration #250

Open
wants to merge 41 commits into
base: master
Choose a base branch
from
Open

Textmodel integration #250

wants to merge 41 commits into from

Commits on Jul 19, 2022

  1. Integrate ULMFiT (initial)

    @Chandu-4444
    Chandu-4444 committed Jul 19, 2022
    Configuration menu
    Copy the full SHA
    8194f3f View commit details
    Browse the repository at this point in the history

  2. Add Paragraph to train_classifier

    @Chandu-4444
    Chandu-4444 committed Jul 19, 2022
    Configuration menu
    Copy the full SHA
    7662230 View commit details
    Browse the repository at this point in the history

Commits on Jul 21, 2022

  1. Add batchseq to pad batch (naive version)

    @Chandu-4444
    Chandu-4444 committed Jul 21, 2022
    Configuration menu
    Copy the full SHA
    1418e50 View commit details
    Browse the repository at this point in the history

  2. Remove Project.toml changes.

    @Chandu-4444
    Chandu-4444 committed Jul 21, 2022
    Configuration menu
    Copy the full SHA
    b682105 View commit details
    Browse the repository at this point in the history

Commits on Jul 24, 2022

  1. Add vocab_size to TextClassificationTask

    @Chandu-4444
    Chandu-4444 committed Jul 24, 2022
    Configuration menu
    Copy the full SHA
    c1064bc View commit details
    Browse the repository at this point in the history

Commits on Jul 25, 2022

  1. Add vocab_size to encodings

    @Chandu-4444
    Chandu-4444 committed Jul 25, 2022
    Configuration menu
    Copy the full SHA
    345ced1 View commit details
    Browse the repository at this point in the history

  2. Test batches integration with model.

    @Chandu-4444
    Chandu-4444 committed Jul 25, 2022
    Configuration menu
    Copy the full SHA
    46b6826 View commit details
    Browse the repository at this point in the history

  3. Update load_batchseq function.

    @Chandu-4444
    Chandu-4444 committed Jul 25, 2022
    Configuration menu
    Copy the full SHA
    388e8ac View commit details
    Browse the repository at this point in the history

Commits on Jul 29, 2022

  1. Clean up useless code from TextModels.jl.

    @Chandu-4444
    Chandu-4444 committed Jul 29, 2022
    Configuration menu
    Copy the full SHA
    8bfe705 View commit details
    Browse the repository at this point in the history

Commits on Aug 2, 2022

  1. Update FastText/src/models/pretrain_lm.jl 

    Co-authored-by: Brian Chen <[email protected]>
    @Chandu-4444 @ToucheSir
    Chandu-4444 and ToucheSir authored Aug 2, 2022
    Configuration menu
    Copy the full SHA
    2482aaa View commit details
    Browse the repository at this point in the history

  2. Update FastText/src/models/dataloader.jl 

    Co-authored-by: Brian Chen <[email protected]>
    @Chandu-4444 @ToucheSir
    Chandu-4444 and ToucheSir authored Aug 2, 2022
    Configuration menu
    Copy the full SHA
    8bc930d View commit details
    Browse the repository at this point in the history

  3. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Brian Chen <[email protected]>
    @Chandu-4444 @ToucheSir
    Chandu-4444 and ToucheSir authored Aug 2, 2022
    Configuration menu
    Copy the full SHA
    3882b1d View commit details
    Browse the repository at this point in the history

  4. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Brian Chen <[email protected]>
    @Chandu-4444 @ToucheSir
    Chandu-4444 and ToucheSir authored Aug 2, 2022
    Configuration menu
    Copy the full SHA
    3057989 View commit details
    Browse the repository at this point in the history

  5. Add reset! for AWD_LSTM. 

    Minor changes as suggested by @ToucheSir
    @Chandu-4444
    Chandu-4444 committed Aug 2, 2022
    Configuration menu
    Copy the full SHA
    307fde1 View commit details
    Browse the repository at this point in the history

Commits on Aug 8, 2022

  1. Add textlearner.

    @Chandu-4444
    Chandu-4444 committed Aug 8, 2022
    Configuration menu
    Copy the full SHA
    075a21e View commit details
    Browse the repository at this point in the history

  2. Complere text classification pipeline.

    @Chandu-4444
    Chandu-4444 committed Aug 8, 2022
    Configuration menu
    Copy the full SHA
    f16ec2c View commit details
    Browse the repository at this point in the history

Commits on Aug 18, 2022

  1. Upadate LanguageModel to use Flux.reset!. 

    Change `AWD_LSTM` to `WeightDroppedLSTM`
    @Chandu-4444
    Chandu-4444 committed Aug 18, 2022
    Configuration menu
    Copy the full SHA
    3469630 View commit details
    Browse the repository at this point in the history

Commits on Aug 23, 2022

  1. Include models.jl file.

    @Chandu-4444
    Chandu-4444 committed Aug 23, 2022
    Configuration menu
    Copy the full SHA
    974a622 View commit details
    Browse the repository at this point in the history

  2. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 23, 2022
    Configuration menu
    Copy the full SHA
    0d44bbd View commit details
    Browse the repository at this point in the history

  3. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 23, 2022
    Configuration menu
    Copy the full SHA
    4ad9a12 View commit details
    Browse the repository at this point in the history

  4. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 23, 2022
    Configuration menu
    Copy the full SHA
    080a018 View commit details
    Browse the repository at this point in the history

  5. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 23, 2022
    Configuration menu
    Copy the full SHA
    922334d View commit details
    Browse the repository at this point in the history

  6. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 23, 2022
    Configuration menu
    Copy the full SHA
    ce34be1 View commit details
    Browse the repository at this point in the history

  7. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 23, 2022
    Configuration menu
    Copy the full SHA
    6cea902 View commit details
    Browse the repository at this point in the history

  8. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 23, 2022
    Configuration menu
    Copy the full SHA
    5159fb8 View commit details
    Browse the repository at this point in the history

  9. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 23, 2022
    Configuration menu
    Copy the full SHA
    c6b69f7 View commit details
    Browse the repository at this point in the history

Commits on Aug 24, 2022

  1. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Aug 24, 2022
    Configuration menu
    Copy the full SHA
    164fe21 View commit details
    Browse the repository at this point in the history

Commits on Aug 26, 2022

  1. Add suggestions and improvements from the call.

    @Chandu-4444
    Chandu-4444 committed Aug 26, 2022
    Configuration menu
    Copy the full SHA
    1ce6df2 View commit details
    Browse the repository at this point in the history

Commits on Aug 28, 2022

  1. Use previous VarDrop code for using in colab.

    @Chandu-4444
    Chandu-4444 committed Aug 28, 2022
    Configuration menu
    Copy the full SHA
    712d9c8 View commit details
    Browse the repository at this point in the history

Commits on Aug 29, 2022

  1. Use NNlib for scalar indexing 

    at `DroppedEmbeddings`.
    @Chandu-4444
    Chandu-4444 committed Aug 29, 2022
    Configuration menu
    Copy the full SHA
    6d6504b View commit details
    Browse the repository at this point in the history

Commits on Aug 31, 2022

  1. Updates to Project.toml

    @Chandu-4444
    Chandu-4444 committed Aug 31, 2022
    Configuration menu
    Copy the full SHA
    5af6edb View commit details
    Browse the repository at this point in the history

Commits on Sep 1, 2022

  1. Modify type params for LanguageModel and 

    `TextClassifier`.
    @Chandu-4444
    Chandu-4444 committed Sep 1, 2022
    Configuration menu
    Copy the full SHA
    659e6d1 View commit details
    Browse the repository at this point in the history

  2. Update FastText/src/models/train_text_classifier.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Sep 1, 2022
    Configuration menu
    Copy the full SHA
    0a151b2 View commit details
    Browse the repository at this point in the history

  3. Update FastText/src/models/train_text_classifier.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Sep 1, 2022
    Configuration menu
    Copy the full SHA
    12bc9ab View commit details
    Browse the repository at this point in the history

Commits on Sep 6, 2022

  1. Update dtypes to avoid CuArray errors.

    @Chandu-4444
    Chandu-4444 committed Sep 6, 2022
    Configuration menu
    Copy the full SHA
    35c345f View commit details
    Browse the repository at this point in the history

  2. Add callable TextClassifier

    @Chandu-4444
    Chandu-4444 committed Sep 6, 2022
    Configuration menu
    Copy the full SHA
    cceee46 View commit details
    Browse the repository at this point in the history

Commits on Sep 8, 2022

  1. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Sep 8, 2022
    Configuration menu
    Copy the full SHA
    f7d51f6 View commit details
    Browse the repository at this point in the history

  2. Update FastText/src/models/custom_layers.jl 

    Co-authored-by: Kyle Daruwalla <[email protected]>
    @Chandu-4444 @darsnack
    Chandu-4444 and darsnack authored Sep 8, 2022
    Configuration menu
    Copy the full SHA
    90c9a79 View commit details
    Browse the repository at this point in the history

Commits on Sep 12, 2022

  1. Update Flux.reset!()

    @Chandu-4444
    Chandu-4444 committed Sep 12, 2022
    Configuration menu
    Copy the full SHA
    7e7de6d View commit details
    Browse the repository at this point in the history

Commits on Sep 13, 2022

  1. Update few Flux.dropout functions.

    @Chandu-4444
    Chandu-4444 committed Sep 13, 2022
    Configuration menu
    Copy the full SHA
    c1418b3 View commit details
    Browse the repository at this point in the history

  2. Update code to avoid non-differentiable error 

    at `Flux.rng_from_array`
    @Chandu-4444
    Chandu-4444 committed Sep 13, 2022
    Configuration menu
    Copy the full SHA
    2c04d19 View commit details
    Browse the repository at this point in the history