Eisen: a python package for solid deep learning
arXiv:2004.02747
Abstract
Eisen is an open source python package making the implementation of deep learning methods easy. It is specifically tailored to medical image analysis and computer vision tasks, but its flexibility allows extension to any application. Eisen is based on PyTorch and it follows the same architecture of other packages belonging to the PyTorch ecosystem. This simplifies its use and allows it to be compatible with modules provided by other packages. Eisen implements multiple dataset loading methods, I/O for various data formats, data manipulation and transformation, full implementation of training, validation and test loops, implementation of losses and network architectures, automatic export of training artifacts, summaries and logs, visual experiment building, command line interface and more. Furthermore, it is open to user contributions by the community. Documentation, examples and code can be downloaded from http://eisen.ai.
References in corpus (4)
- A large annotated medical image dataset for the development and evaluation of segmentation algorithms
- TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
- On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task
- DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images