### 
### === README
### === 4D_128_cube_topological_dataset
###  


### === AUTHORS
Khalil Mathieu Hannouch and Stephan Chalup

### === LICENSE
All supplementary material uses the following license:
Creative Commons Attribution 4.0 International (CC BY 4.0)
https://protect-au.mimecast.com/s/JU4LC71RMGTXJVBOu8O498?domain=creativecommons.org

This license permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original authors, Khalil Mathieu Hannouch and Stephan Chalup, and the associated paper (https://protect-au.mimecast.com/s/PWcJCmO5k3TorPQmf4MSH1?domain=arxiv.org), provide a link to the Creative Commons license, and indicate if changes were made.


### === ACKNOWLEDGMENTS AND DISCLOSURE OF FUNDING
This research was supported by the Australian Government through the ARC's Discovery Projects funding scheme (DP210103304 `Estimating the Topology of Low-Dimensional Data Using Deep Neural Networks'). The views expressed herein are those of the authors and are not necessarily those of the Australian Government or Australian Research Council. The first author was supported by a PhD scholarship from the University of Newcastle associated with this grant.

### === CONTENTS

The supplementary materials comprise of the dataset and two 4D visualisation in video format. The dataset can be downloaded as either a single approximately 30GB .zip file, or as a series of 20 1.5GB .zip files.

### === USING THE DATASET

Each .npz file sample contains three elements:
1. data
2. bettiNumbers
3. objects: a count of B4, S1xB3, S2xB2, and S1xS1xB2 in the sample

load sample using: 
>>> import numpy as np
>>> loadedSample = np.load(‘4d_mixed_#0_1.npz’)
>>> cube = loadedSample[‘data’]
>>> labelBetti = loadedSample[‘bettiNumbers’]
>>> labelObjs = loadedSample[‘objects’]

### === DATASET PARAMETERS

sampleNumber: 
0 to 31999

Cube dimensions: 
- 128x128x128x128

Boundary:
- 1 toxel
 
Spacing:
- radius: [6.5,uncapped)

Ball: 
- radius  a: [7.6,24.1]

S1xB3:
- radius  a: [4.2,13.3]
- radius  R: [8.4,26.7]

S2xB2:
- radius  a: [3.2,10.1]
- radius  R: [6.4,20.3]

S1xS1xB2:
- deg alpha: [0,pi/2]
- radius  a: [2.4,6.4]
- radius  r: [4.8,12.8]
- radius  R: [4.8,25.6]