Giter VIP home page Giter VIP logo

scoreperformer's People

Contributors

ilya16 avatar

Stargazers

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

Watchers

 avatar

scoreperformer's Issues

Running `train.py` results in `ValueError` from dataclasses

I'm trying to play a bit with ScorePerformer to understand it better. I installed all requirements in a new environment, and I did not change anything in the code. When trying to execute the train.py script, I'm getting an error from dataclasses:

$ python scoreperformer/train.py
Traceback (most recent call last):
  File "/home/user/ScorePerformer/scoreperformer/train.py", line 5, in <module>
    from scoreperformer.experiments import Trainer
  File "/home/user/ScorePerformer/scoreperformer/experiments/__init__.py", line 1, in <module>
    from .trainer import Trainer
  File "/home/user/ScorePerformer/scoreperformer/experiments/trainer.py", line 22, in <module>
    from scoreperformer.models.base import Model
  File "/home/user/ScorePerformer/scoreperformer/models/__init__.py", line 2, in <module>
    from .scoreperformer import (
  File "/home/user/ScorePerformer/scoreperformer/models/scoreperformer/__init__.py", line 1, in <module>
    from .embeddings import TupleTokenEmbeddings, TupleTokenLMHead, TupleTokenTiedLMHead
  File "/home/user/ScorePerformer/scoreperformer/models/scoreperformer/embeddings.py", line 12, in <module>
    from scoreperformer.modules.transformer import DiscreteContinuousEmbedding, DiscreteDenseContinuousEmbedding
  File "/home/user/ScorePerformer/scoreperformer/modules/transformer/__init__.py", line 21, in <module>
    from .transformer import (
  File "/home/user/ScorePerformer/scoreperformer/modules/transformer/transformer.py", line 34, in <module>
    @dataclass
     ^^^^^^^^^
  File "/home/user/miniconda3/envs/ScorePerformer/lib/python3.11/dataclasses.py", line 1232, in dataclass
    return wrap(cls)
           ^^^^^^^^^
  File "/home/user/miniconda3/envs/ScorePerformer/lib/python3.11/dataclasses.py", line 1222, in wrap
    return _process_class(cls, init, repr, eq, order, unsafe_hash,
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/miniconda3/envs/ScorePerformer/lib/python3.11/dataclasses.py", line 958, in _process_class
    cls_fields.append(_get_field(cls, name, type, kw_only))
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/miniconda3/envs/ScorePerformer/lib/python3.11/dataclasses.py", line 815, in _get_field
    raise ValueError(f'mutable default {type(f.default)} for field '
ValueError: mutable default <class 'scoreperformer.modules.transformer.attention.AttentionConfig'> for field attention is not allowed: use default_factory

I know that I should probably pass some parameters to the script (e.g. data location), but I assume that the script should error due to missing parameters rather than this one.

By the way, having an example of a training command would be very valuable!

Access to alignment and preprocessing pipeline

Hello,

First, thanks for sharing your work, your paper was very interesting!

Note: The code for the alignment and preprocessing of score and performance data is deliberately not made available. It can be discussed and released upon request and demand.

I would be interested in a release of the alignment and preprocessing pipeline you used, as I would like to try ScorePerformer on some other data. Would that be possible?

Thank you in advance!

Thank you for sharing this work :)

@ilya16 Hey Ilya!

Thank you for the follow and thank you for sharing your work. I saw your paper on ISMIR (congrats) and I am happy to see the code and colab on GitHub.

I will be checking it out soon and I have some questions for you. Please watch out for my email as I would prefer to discuss stuff in private rather than here.

Anyway, hope to talk to you soon.

Alex

P.S. You can close this issue. I just wanted to say hi.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.