diff --git a/docs/usage/train/augmentation.md b/docs/usage/train/augmentation.md index f5971924f30c198c8d188520b1878f1cc8bdb366..c066538d6a688c819470276fff2d729495d83e17 100644 --- a/docs/usage/train/augmentation.md +++ b/docs/usage/train/augmentation.md @@ -16,6 +16,8 @@ This page lists data augmentation transforms used in DAN. ### PieceWise Affine +:warning: This transform is temporarily removed from the pipeline until [this issue](https://github.com/albumentations-team/albumentations/issues/1442) is fixed. + | | PieceWiseAffine | | ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Description | This transformation also applies local distortions but with a larger grid than EslasticTransform. | @@ -125,7 +127,6 @@ This page lists data augmentation transforms used in DAN. * Data augmentation is applied with a probability of 0.9. * In this case, two transformation are randomly selected to be applied. -* `ElasticTransform` and `PieceWiseAffine` cannot be applied on the same image. * Reproducibility is possible by setting `random.seed` and `np.random.seed` (already done in `dan/ocr/document/train.py`) * Examples with new pipeline: