matsui-k-dmj / jigsaw-unintended-bias Goto Github PK
View Code? Open in Web Editor NEWKaggle: Jigsaw Unintended Bias in Toxicity Classification
Kaggle: Jigsaw Unintended Bias in Toxicity Classification
普通にしないだけでは変わらない。
説明 | mean weighted AUC | LB | train kernel | prediction kernel | 備考 | epoch | cosannealing | initilaization | aux | sample weighing | n_seeds | nonbinary |
---|---|---|---|---|---|---|---|---|---|---|---|---|
MVP-Train 20ep LSTM decent initial | 0.9286(last19 | MVP-Train 20ep LSTM decent initial | Kaggle | ちょい過学習 | 20 | T | T | T | 2 | ||||
nonbinary target MVP-Train 20ep LSTM | 0.9286(last 12 | nonbinary target MVP-Train 20ep LSTM | Kaggle | もとのやつと変わらん、、、 | 20 | T | T | T | T |
Annealing しなくていいっぽい
説明 | mean weighted AUC | LB | train kernel | prediction kernel | 備考 | epoch | cosannealing | initilaization | aux |
---|---|---|---|---|---|---|---|---|---|
mvp seed 4, epoch20: MVP-Train 20epoch | 0.9296(last 15 | MVP-Train 20epoch | Kaggle | 最後ちょっと過学習?, annealしないほうがよさげ | 20 | F | F | T | ||
MVP-Train CosAnn 20epoch | 0.9289(last18 | MVP-Train CosAnn 20epoch | Kaggle | ちょい過学習 | 20 | T | F | T |
10だと学習しきれてない
20のほうがいい
説明 | mean weighted AUC | LB | train kernel | prediction kernel | 備考 | epoch | cosannealing | initilaization | aux |
---|---|---|---|---|---|---|---|---|---|
mvp seed 10: MVP-Train | 0.928 (epoch weighted | MVP-Train | Kaggle | 学習しきれてない | 10 | F | F | T | ||
mvp seed 4, epoch20: MVP-Train 20epoch | 0.9296(last 15 | MVP-Train 20epoch | Kaggle | 最後ちょっと過学習?, annealしないほうがよさげ | 20 | F | F | T |
説明 | mean weighted AUC | LB | train kernel | prediction kernel | 備考 | epoch | cosannealing | initilaization | aux |
---|---|---|---|---|---|---|---|---|---|
MVP-Train 20ep LSTM decent initial | 0.9286(last19 | MVP-Train 20ep LSTM decent initial | Kaggle | ちょい過学習 | 20 | T | T | T | ||
mvp lstm cosanneal no aux | 0.9255(last19 | mvp lstm cosanneal no aux | Kaggle | 過学習、雑魚い | 20 | T | T | F |
現時点では誤差でしかない。あとでいろいろためそう
説明 | mean weighted AUC | LB | train kernel | prediction kernel | 備考 | epoch | cosannealing | initilaization | aux |
---|---|---|---|---|---|---|---|---|---|
MVP-Train 20ep decent initial GRU | 0.9287 | MVP-Train 20ep decent initial GRU | Kaggle | GRU, 過学習気味 | 20 | T | T | T | ||
MVP-Train 20ep LSTM decent initial | 0.9286(last19 | MVP-Train 20ep LSTM decent initial | Kaggle | ちょい過学習 | 20 | T | T | T |
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.