Skip to main content

No project description provided

Project description

pytorch-randaugment

Unofficial PyTorch Reimplementation of AutoAugment and RandAugment.

Code taken from https://github.com/DeepVoltaire/AutoAugment and https://github.com/jizongFox/uda

How to install:

pip install randaugment

How to use:

from autoaugment import RandAugment, ImageNetPolicy
data = ImageFolder(rootdir, transform=transforms.Compose(
                        [
                            transforms.RandomCrop(32, padding=4, fill=128), # fill parameter needs torchvision installed from source
                            transforms.RandomHorizontalFlip(), 
                            RandAugment(),
                            #ImageNetPolicy(),
                            transforms.ToTensor(), 
                            Cutout(size=16), # (https://github.com/uoguelph-mlrg/Cutout/blob/master/util/cutout.py)
                            transforms.Normalize(...)
                        ])
)
loader = DataLoader(data, ...)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

randaugment-1.0.2.tar.gz (5.4 kB view hashes)

Uploaded source

Built Distribution

randaugment-1.0.2-py3-none-any.whl (6.8 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page