https://github.com/eve-ning/opal-v2

Rhythm Game Score Estimation through Simple Embedding Optimization
https://github.com/eve-ning/opal-v2

machine-learning osu osumania python pytorch pytorch-lightning streamlit

Last synced: 2 months ago
JSON representation

Rhythm Game Score Estimation through Simple Embedding Optimization

• Host: GitHub
• URL: https://github.com/eve-ning/opal-v2
• Owner: Eve-ning
• Created: 2024-01-03T12:54:06.000Z (12 months ago)
• Default Branch: master
• Last Pushed: 2024-08-17T13:47:08.000Z (4 months ago)
• Last Synced: 2024-08-18T02:56:26.197Z (4 months ago)
• Topics: machine-learning, osu, osumania, python, pytorch, pytorch-lightning, streamlit
• Language: Python
• Homepage: https://opal-v2.streamlit.app/
• Size: 19.9 MB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# :arrow_forward: [**Try Out Opal V2 on Streamlit**](https://opal-v2.streamlit.app/)

# :comet: opal-v2

opal-v2 is *another* accuracy-prediction model.

It's an improvement over the previous [opal](https://github.com/Eve-ning/opal),

which used a heavier algorithm, thus slower and larger model.

The clearest difference you can see is the fact that opal v2 offers a more

explainable approach to skill/rating estimation while opal v1, because of its

internal complexity, requires a lot of black-box testing to achieve this.

The details of implementation of this model is mostly in my blog post:

[opal v2: Explainable Map and Player Embedding Optimation with Guided Constraints](https://eve-ning.github.io/2024/07/26/opal-v2.html)

## :brain: AlphaOsu!

As usual, opal doesn't provide recommendations, however, you can try out [AlphaOsu!](https://alphaosu.keytoix.vip/).

- [AlphaOsu! GitHub](https://github.com/AlphaOSU)

- [Support AlphaOsu!](https://alphaosu.keytoix.vip/support)