matsui-k-dmj / jigsaw-unintended-bias Goto Github PK
View Code? Open in Web Editor NEWKaggle: Jigsaw Unintended Bias in Toxicity Classification
jigsaw-unintended-bias's People
Watchers
jigsaw-unintended-bias's Issues
targetはbinalizeしたほうがいいのか
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 |
Cosine Annealingしなくていい
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 |
10epochか20epochか
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 |
auxは必要
| 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 |
lstmかgruか
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 |
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.