Comments (2)
Thanks for your question.
Unfortunately, there is no silver bullet to decomposition mappings.
For instance, we built the Chinese character decomposition table by using the following public CCD table
https://commons.wikimedia.org/wiki/Commons:Chinese_characters_decomposition
For complete-compositional languages such as Korean and Thai,
we parse Unicode to extract the component labels as follows:
- Korean: https://github.com/clovaai/dmfont/blob/master/datasets/kor_decompose.py#L29-L44
- Thai: https://github.com/clovaai/dmfont/blob/master/datasets/thai_decompose.py#L83-L101
For Japanse, as far as I know, you can use the CCD table for Kanji (there might be missing items in the CCD table, but as far as I know, most characters in popular Kanji are covered by the CCD table).
For Kana (Hiragana, Katakana), to my knowledge, there is no specific decomposition rule by its design. Hence, I suggest you manually build a new decomposition table for Kana (e.g., dakuten) or treat them as an "atomic" (i.e., a character has only one component) for convenience.
from lffont.
Closing the issue, assuming my answer resolves the problem.
Please re-open the issue as necessary.
from lffont.
Related Issues (20)
- Style transfer for a single font HOT 7
- how to "Build meta file to dump lmdb environment" and how to "python build_dataset.py "? HOT 2
- During training, the model stops at "Start training..." HOT 13
- lmdb_path HOT 7
- Training interrupted by validation HOT 10
- Question about p1dataset.py HOT 2
- Pre-trained model for Korean fonts generation HOT 2
- The label number of the chn_decomposed HOT 8
- Question about training
- How to use the data produced by the build_dataset.py file during training HOT 9
- Question about the classfiers for calculating FID ACC(S) and ACC(C) HOT 3
- Hello, may I ask how to process data when using images as training sets in LFFont? HOT 1
- KeyError: '71FC' HOT 3
- IndexError: list index out of range HOT 4
- ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 2 dimensions. The detected shape was (27, 2) + inhomogeneous part. HOT 4
- Question about korean generator HOT 2
- 数据集 HOT 1
- data set HOT 1
- data set HOT 4
- about phase 1 training HOT 2
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 lffont.