The goal of our research problem is illustrated below: given a tile set (a) and a 2D region to be filled (b), we aim to produce a tiling (c) that maximally covers the interior of the given region without overlap or hole between the tile instances.
This project is implemented in Python 3.7. You need to install the following packages to run our program.
We provide the following entry points for researchers to try our project:
Tiling-GUI.py
, you can use our interface to draw a tiling region and preview the tiling results interactively. Tiling-Shape.py
, you can use our pre-trained models, or IP solver, to solve a tiling problem by specifying a tiling region (from silhouette image) and a tile set.data
folder, create a new folder with new files that describe your new tile sets. After that, you need to edit the global configuration file inputs/config.py
to let the system know you your new tile set.tiling/gen_complete_super_graph.py
, the generated files will be stored in the folder you created in Step (1).solver/ml_solver/gen_data.py
, the data will be stored in the path recorded in file inputs/config.py
.solver/ml_solver/network_train.py
.In this program, we have a global configuration file inputs/config.py
, which plays a very important role to control the behavior of the programs, such as which tile set you want to work with, the stored location of the trained networks, or how many training data you will create, etc.
If you met problems or any question on this project, contact us at [haoxu@cse.cuhk.edu.hk] or [a03090@gmail.com]