Giter VIP home page Giter VIP logo

cup's People

Contributors

tbabm avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar

Forkers

megumigachi czzc22 bibosx0 blindspoter01 clumnsgy-ll zhuang-liu-maker zhang-ge-hao

cup's Issues

Why here needs "hypo_ids = topk_positions / vocab_size"

CUP/models/beam.py

Line 91 in 43ebf64

hypo_ids = topk_positions / vocab_size

I'm afraid that the above code causes the following line error.

CUP/models/beam.py

Line 122 in 43ebf64

new_hypo_sents.append(self.live_hypo_sents[hypo_id] + [word_id]) 

The error log is shown here:
Traceback (most recent call last):
  File "infer.py", line 100, in <module>
    main()
  File "infer.py", line 96, in main
    infer(args)
  File "infer.py", line 91, in infer
    infer_instance.infer()
  File "infer.py", line 65, in infer
    hypos = self.beam_search(test_set)
  File "infer.py", line 55, in beam_search
    example_hypos = self._model.beam_search(example, self.beam_size, self.max_dec_step, BeamClass)
  File "D:\Projects\CommentUpdate_cup\models\updater.py", line 175, in beam_search
    hypos = self.nl_decoder.beam_search(example, beam_size, max_dec_step, BeamClass, **decoder_kwargs)
  File "D:\Projects\CommentUpdate_cup\models\decoder.py", line 273, in beam_search
    state_tm1 = beam.step(words_log_prob, state_tm1)
  File "D:\Projects\CommentUpdate_cup\models\beam.py", line 122, in step
    new_hypo_sents.append(self.live_hypo_sents[hypo_id] + [word_id])
TypeError: list indices must be integers or slices, not float

Some questions about datasets.

Dear authors.

Thanks for your great work. Recently, our group is trying to train your model with our dataset. I see there are a lot of "idx" in .jsonl files of your dataset, but we can not understand what is this for. To avoid potential bias, could you tell us what "idx" means? In addition, there are some .pkl files in your dataset, could you tell us how are these files generated? Thanks a lot.

Best wishes

The generator of edit sequence

Dear authors.

Thanks for your great work. Recently, we are trying to follow CUP and train your model on our dataset. While it seems that you did not provide the edit sequence generator. To avoid potential bias, if it’s convenient, could you provide the related code? Thanks a lot.

Best
Bo.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.