storyllka.blogg.se - Download in the air lab

For details, consider the NOTICE file.TROX understands the art of competently handling air like no other company. We deeply appreciate the help of the following people:ĪirLab depends on several third party open source project which are included as library. Thus, if you find and/or fix bugs or extend the software please contribute as well and let us know or make a pull request. We released AirLab to contribute to the community. "AirLab: Autograd Image Registration Laboratory". Robin Sandkuehler, Christoph Jud, Simon Andermatt, and Philippe C. If you can use this software in any way, please cite us in your publications: For details, consider the LICENSE and NOTICE file.

Robin Sandkuehler - initial work ( Christoph Jud - initial work ( Simon Andermatt - project supportĬheck out our AIRLab tutorial at MICCAI 2019 in Shenzhen: LicenseĪirLab is licensed under the Apache 2.0 license.

The project started in the Center for medical Image Analysis & Navigation research group of the University of Basel. The project depends on following libraries: In order to process larger image data a GPU is required. Currently, its CPU implementation is quite memory consuming. The convolution operation, which is frequently used in AirLab, is performed in PyTorch. We recommend to start with the example applications provided in the example folder.

Make sure that following python libraries are installed:.

We refer to our arXiv preprint 2018 for a detailed introduction of AirLab and its feature.Īuthors: Robin Sandkuehler and Christoph Judįollow us on Twitter to get informed about the most recent features, achievements and bugfixes. Furthermore, it borrows key functionality from PyTorch (autograd and optimization) which is of course not limited to deep learning methods. It is rather a laboratory for image registration algorithms for rapid prototyping and reproduction.

It profits therefore from recent advances made by the machine learning community.ĪirLab is not meant to replace existing registration frameworks nor it implements deep learning methods only. In addition, the device on which the computations are performed, on a CPU or a GPU,ĪirLab is implemented in Python using PyTorch as tensor and optimization library and SimpleITK for basic image IO.

The unique feature of AirLab is, that the analytic gradients of the objective function are computed automatically with fosters rapid prototyping. It provides an environmentįor rapid prototyping and reproduction of registration algorithms. AirLab is an open laboratory for medical image registration.