State-of-the-art data augmentation search algorithms in PyTorch
Project description
MuarAugment
Description
MuarAugment is a package providing the easiest way to a state-of-the-art data augmentation pipeline.
How to use
You can install MuarAugment
via PIP:
!pip install muaraugment
Example (temp: tutorials and working examples coming soon)
from muar.augmentations import BatchRandAugment, MuAugment
# muar augmentations
rand_augment = BatchRandAugment(N_TFMS=3, MAGN=4)
mu_augment = MuAugment(rand_augment, N_COMPS=4, SELECTED=2)
# model
model = LitClassifier(mu_augment)
# data
train, val, test = mnist()
# train
trainer = Trainer()
trainer.fit(model, train, val)
Tutorials
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 Distribution
MuarAugment-1.1.0.tar.gz
(11.4 kB
view hashes)
Built Distribution
Close
Hashes for MuarAugment-1.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 057b7b9f9572fd38e873c6f78037186c604042a70eb5f31673ae0901440f97ac |
|
MD5 | edaf9297ba8abdee7c939793f74ac3b6 |
|
BLAKE2b-256 | 9c8b7b8e55df1cc016399a08848cb8204ecd58d056f68e32ff1a13797cb91752 |