README.md

Dataset: ModelNet10

http://modelnet.cs.princeton.edu/#

Data preparation

https://github.com/guoguo12/modelnet-cnn3d_bn

.off -(1.voxelize)-> .binvox -(2.read)-> Numpy array

1. Voxelize
   Read in [.off] file and change it into [.binvox] file of binary voxel data , using binvox program.

2. Read
   Read [.binvox] file into Numpy array with (30,30,30) shaped elements, using binvox_rw.py and prepare_data.py.

Network architecture

very simple: input-ccp-ccp-dense-output

Visualization

[.binvox] file can be viewed here.

Study(paper review)

https://docs.google.com/presentation/d/183N5PUKAzACj1IkOT4K3F5m1iN-x-KaPIufhYXkqw5E/edit?usp=sharing