Comments (1)
목적
(1) 외부 데이터로 사전 학습한 뒤 주어진 데이터를 학습하면 성능이 개선되는지 확인
(2) vocab size(토큰 수)를 늘렸을 때 성능 저하 또는 향상이 발생하는지 확인
과정
- List_of_LaTeX_symbols를 참고하여 새로운 Latex 토큰을 추출한 뒤, 기존 tokens.txt와 병합 => 총 576개 토큰을 얻음(공유폴더첨부-tokens576.txt)
- 이후 IM2LATEX으로부터 576개 토큰 외 다른 토큰은 포함되지 않은 이미지/GT를 추출 => 총 30,804개 이미지 추출
- SATRN에 학습 진행: RGB3, Adam, BS36, CustumCosine
추가적으로 확인할 것
- 576개 토큰의 vocab을 활용한 SATRN 학습(IM2LATEX 활용X) => 목적 (1), (2)에 대한 명확한 확인을 위해
from p4-fr-sorry-math-but-love-you.
Related Issues (20)
- Attention - RGB 3 실험
- ICDAR 2015 - 주요 모델 논문
- Attention - RGB3 + size(256,256) HOT 1
- Pretrained-BERT for SATRN HOT 1
- 앙상블 HOT 1
- SATRN - RGB 3 실험
- SATRN - Size256, RGB3 실험
- SATRN - AdamW 실험
- SATRN - FAST EXP HOT 3
- SATRN - 논문 내용 실험 HOT 2
- Attention - CustomCosine, flip test
- BEAM-SEARCH HOT 4
- SATRN - Dataset 0.1 ratio Basic (비교용)
- SATRN - CLAHE 실험
- SEED - BERT 적용해보기
- 인코더 & 디코더 lr 개별 부여
- BERT 모델 활용 후처리 파이프라인 개발 HOT 1
- 디코딩 과정 상의 Postprocessor
- REFACTORING HOT 1
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.
from p4-fr-sorry-math-but-love-you.