ModelNet10‑dataset Overview

Dataset Description

• Original dataset size: Approximately 2.2 Gigabytes
• NumPy file size: Approximately 8 Gigabytes
• Compressed file size: Approximately 32 Megabytes

Dataset Contents

• Contains the NumPy array file of the ModelNet10 3D Vision dataset.

Usage Example

import gzip
import numpy as np
with gzip.open('modelnet10.npy.gz', 'rb') as f:
    arr = np.load(f)
    print(type(arr), arr.shape)

Output:

<class 'numpy.ndarray'> (3992, 1, 64, 64, 64)

Visualization Example:

import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.gca(projection='3d')
ax.voxels(arr[78][0], facecolors='red')
plt.show()

Resulting Image:

Dataset Generation Script

• A script for converting the original OFF files into the final format is provided in the scripts folder.