Albumentations is an image augmentation library and computer vision preprocessing tool designed to expand datasets for deep learning models. It provides a collection of transformations that modify pixel values and spatial geometry to increase the diversity of training samples and improve model generalization. The library supports both 2D image augmentation and 3D volumetric data augmentation. It handles a variety of labels alongside images, ensuring that bounding boxes, keypoints, and segmentation masks remain accurately aligned when spatial transformations are applied. The tool incorporates
Parametric differentiable curves with PyTorch for continuous embeddings, shape-restricted models, or KANs
A unified ensemble framework for PyTorch to improve the performance and robustness of your deep learning model.
functorch is JAX-like composable function transforms for PyTorch.
The main features of zou3519/functorch are: PyTorch Utilities.
Open-source alternatives to zou3519/functorch include: ag14774/diffdist. albu/albumentations — Albumentations is an image augmentation library and computer vision preprocessing tool designed to expand datasets for… alexshtf/torchcurves — Parametric differentiable curves with PyTorch for continuous embeddings, shape-restricted models, or KANs. amirgholami/hessianflow. amirgholami/pyhessian — PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks. aaronx121/ensemble-pytorch — A unified ensemble framework for PyTorch to improve the performance and robustness of your deep learning model.
