A PyTorch library for augmentations of 3d data.
Project description
Voxelmentations
Voxelmentations is a Python library for 3d image (voxel) augmentation. Voxel augmentation is used in deep learning to increase the quality of trained models. The purpose of voxel augmentation is to create new training samples from the existing data.
Here is an example of how you can apply some augmentations from voxelmentations to create new voxel from the original one:
Table of contents
Authors
Rostislav Epifanov — Researcher in Novosibirsk
Installation
Installation from PyPI:
pip install voxelmentations
Installation from GitHub:
pip install git+https://github.com/rostepifanov/voxelmentations
A simple example
import numpy as np
import voxelmentations as V
# Declare an augmentation pipeline
transform = V.Sequential([
V.Flip(p=0.5),
])
# Create example 3d image (height, width, depth, nchannels)
input = np.ones((32, 32, 32, 1))
# Augment exg
transformed = transform(voxel=input)
output = transformed['voxel']
List of augmentations
The list of transforms:
Citing
If you find this library useful for your research, please consider citing:
@misc{epifanov2024exgment,
Author = {Rostislav Epifanov},
Title = {voxelmentations},
Year = {2024},
Publisher = {GitHub},
Journal = {GitHub repository},
Howpublished = {\url{https://github.com/rostepifanov/voxelmentations}}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Close
Hashes for voxelmentations-0.0.1-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d65af928e68387c56c92870e7c343e0e761b5030f65252e42c5fec82e4fb20ae |
|
MD5 | 6429624cc29aa493f2d92daac826b32d |
|
BLAKE2b-256 | d64770863354dacb13bac423ed70ca0c2a1fbf295fa88bfd098251894d6560e7 |