Closed hreso110100 closed 10 months ago
thank you, please feel free to create PRs (https://github.com/Project-MONAI/MONAI/blob/dev/CONTRIBUTING.md), preferably implementing this using only pytorch and monai APIs would make it easy to maintain for the core dev team.
Thank you I will do my best.
closing because of inactivity @hreso110100 reopen if needed.
Is your feature request related to a problem? Please describe. I recently discoved auto augmentation methods for regular images in pytorch/torchvision docs (e.g. https://pytorch.org/vision/main/generated/torchvision.transforms.AutoAugment.html), but I found out that it is very hard to apply these methods in MONAI/medical domain due to implementation restrictions.
Describe the solution you'd like Due to this problem I started to reimplement these methods to be compatible with MONAI ecosystem (recently I have finished TrivialAugment to be applicable for 3D medical images )
Describe alternatives you've considered At first I tried to use original implementation but it is restricted to 2D images (sometimes even only to RGB images), which is obviously not desired.
Additional context I would like to submit my reimplementation to MONAI, so others will be able to use it as well.