This is an implementation of Pointer Networks to solve the Convex Hull problem. Stacking RNN layers is supported.
- Python 3.x
- TensorFlow 1.2.x
Convex Hull datasets such as "convex hull 5" and "convex hull 5-50" can be downloaded at Link.
training
$ python convex_hull.py --ARG=VALUE
evaluating
$ python convex_hull.py --forward_only=True --beam_width=VALUE --ARG=VALUE
visualizing
$ tensorboard --logdir=DIR
Training on convex hull 5
Training on convex hull 5-50