Skip to content

emanuelemessina/seal

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

85 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SEAL

Structured Encoder for Ancient Logograms

Paper

Presentation

Requirements

pip install -r requirements.txt
pip install -r req-torch.txt

Launch

To train or evaluate the model:

cd model
python launch.py [options...]

Check launch.py or call it with --help to inspect the available options.

Checkpoint

The model checkpoint must be placed under the model folder, next to launch.py

Dataset

The model was trained on SEAL 5864.

This repo also contains the dataset generation code for "SEAL N".

The dataset (test and train folders, image_stats.txt) must be placed inside dataset/output.

About

Structured Encoder for Ancient Logograms

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published