Keywords: data augmentation, deep learning, image classification, image segmentation, 2D, 3D
Data Augmentation is quintessential for training modern AI-based image analysis methods. Through careful modification of the available training data, the training distribution is extended and/or covered in more detail, reducing the potential for overfitting. Batchgenerators is deep-learning framework agnostic and can be integrated into your PyTorch and Tensorflow workloads and more.
Batchgenerators sets itself apart from other data augmentation solutions through its native support of both 2D and 3D images and its support for images from many different domains (not just uint8 RGB images...). It can be applied to segmentation, classification, and other tasks. Bounding boxes are unfortunately not supported.