A package for reproducible vision data augmentation in PyTorch.
Project description
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.
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
RepAug-0.0.1.tar.gz
(5.6 kB
view details)
Built Distribution
File details
Details for the file RepAug-0.0.1.tar.gz.
File metadata
- Download URL: RepAug-0.0.1.tar.gz
- Upload date:
- Size: 5.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 8e7bdb5a69c87d565a061d356fe1f658c2b2df42314b6e17a66cc1ada0cccbee |
|
| MD5 | 5f7300fa837bcd034f378cbf5b56637b |
|
| BLAKE2b-256 | 87e08566b07dc4908416f485dee96356d252b38b20806c6f042e8a8185597610 |
File details
Details for the file RepAug-0.0.1-py3-none-any.whl.
File metadata
- Download URL: RepAug-0.0.1-py3-none-any.whl
- Upload date:
- Size: 8.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 93e6a3657b93e36fc6646f5e8359cb79e2d6ee5199890bc4d62a890bab0a76b3 |
|
| MD5 | 153cc672fe82380907931aa159c0e829 |
|
| BLAKE2b-256 | b79356d009ede37240c24acfc91ab52b841da0c0e88000bcb38e9a7b88e4305f |
