The image/document augmentations in`chug` rely on a number of external influences. Our document oriented`doc_better` torchvision augmentations are influenced by`nougat`, and the`doc_nougat` is a direct adaptation of the[`albumentations`](https://albumentations.ai/) +`cv2` document pipeline in[`nougat`](https://github.com/facebookresearch/nougat). Several image augmentations leverage existing work in the`timm` library.

Also, big thanks to the maintainers of[`webdataset`](https://github.com/webdataset/webdataset) andHuffing Face[`datasets`](https://github.com/huggingface/datasets).

Also, big thanks to the maintainers of[`webdataset`](https://github.com/webdataset/webdataset) andHugging Face[`datasets`](https://github.com/huggingface/datasets).