Metadata-Version: 2.1
Name: RepAug
Version: 0.0.1
Summary: A package for reproducible vision data augmentation in PyTorch.
Author-email: Yiming Ma <yiming.ma.cv@outlook.com>
Project-URL: Homepage, https://github.com/Yiming-M/RepAug
Project-URL: Bug Tracker, https://github.com/Yiming-M/RepAug/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE

# RepAug

**Reproducible vision data augmentation in PyTorch.**

Essentially, images are converted to `torch.Tensor` first to be transformed. You can specify the argument `seed`, which will be passed to `np.random.default_rng`, to make your transform reproducible.

Currently supported transforms:
- RandomColorJitter
- RandomCrop, RandomResizedCrop
- RandomHorizontalFlip, RandomVerticalFlip
- RandomGaussianBlur
- Salt, Pepper
- RandomRotation, Random90Rotation, Random180Rotation

See `illustration.ipynb` for illustrations.

To use this package, you can clone it first and run `python setup.py install`.
