An enhanced zi2zi project [1] with word-oriented data augmentation, feature combination, and transfer learning.
This repo is based on zi2zi project with incremental boost inspired on recent research and our observation on Chinese Characters.
Font2Font
| README.md
└── src/
| └── zi2zi/ # original zi2zi with data aug options
| └── zi2zi_hir/ # + combine levels of features
| └── zi2zi_hir_dis/ # + increase discriminator complexity
| └── zi2zi_hir_morefilter/ # + alternative ways of complexity boost
| PastDiscussion/
| PriorWork/
| Report/
| └── Interim/
| └── Final/
Train zi2zi
change directory to src/zi2zi;
$ make all // prepare data, train, and evaluate on demo word
- tensorflow 0.8
- python 3.x