tag:joss.theoj.org,2005:/papers/tagged/PyTorch?page=2Journal of Open Source Software2022-10-09T08:06:59ZJournal of Open Source Softwarehttps://joss.theoj.orgtag:joss.theoj.org,2005:Paper/37612022-10-09T08:06:59Z2022-10-10T00:01:28ZVolume Segmantics: A Python Package for Semantic Segmentation of Volumetric Data Using Pre-trained PyTorch Deep Learning
Modelsacceptedv0.2.62022-08-03 10:44:21 UTC782022-10-09 08:06:59 UTC720224691OliverN. f.KingDiamond Light Source Ltd., Harwell Science and Innovation Campus, Didcot, Oxfordshire, UK0000-0002-6152-7207DimitriosBellosRosalind Franklin Institute, Harwell Science and Innovation Campus, Didcot, Oxfordshire, UK0000-0002-8015-3191MarkBashamDiamond Light Source Ltd., Harwell Science and Innovation Campus, Didcot, Oxfordshire, UK, Rosalind Franklin Institute, Harwell Science and Innovation Campus, Didcot, Oxfordshire, UK0000-0002-8438-141510.21105/joss.04691https://doi.org/10.5281/zenodo.7143363Pythonhttps://joss.theoj.org/papers/10.21105/joss.04691.pdfsegmentation, deep learning, volumetric, images, pre-trainedtag:joss.theoj.org,2005:Paper/34172022-05-30T22:45:05Z2022-05-31T00:01:36ZDIRECT: Deep Image REConstruction Toolkitacceptedv1.0.12022-03-09 18:05:29 UTC732022-05-30 22:45:05 UTC720224278GeorgeYiasemisNetherlands Cancer Institute, University of AmsterdamNikitaMoriakovNetherlands Cancer Institute, Radboud University Medical CenterDimitriosKarkalousosAmsterdam UMC, Biomedical Engineering and PhysicsMatthanCaanAmsterdam UMC, Biomedical Engineering and PhysicsJonasTeuwenNetherlands Cancer Institute, University of Amsterdam, Radboud University Medical Center10.21105/joss.04278https://doi.org/10.5281/zenodo.6594702Pythonhttps://joss.theoj.org/papers/10.21105/joss.04278.pdfPytorch, Deep Learning, Inverse Problem Solver, Image Processing, Deep MRI reconstruction, Accelerated MRItag:joss.theoj.org,2005:Paper/33272022-04-25T11:47:43Z2022-04-26T00:00:55Z`hessQuik`: Fast Hessian computation of composite functionsacceptedv0.0.12022-02-08 17:55:28 UTC722022-04-25 11:47:43 UTC720224171ElizabethNewmanEmory University, Department of Mathematics0000-0002-6309-7706LarsRuthottoEmory University, Department of Mathematics0000-0003-0803-329910.21105/joss.04171https://doi.org/10.5281/zenodo.6478757Python, Jupyter Notebookhttps://joss.theoj.org/papers/10.21105/joss.04171.pdfpython, pytorch, deep neural networks, input convex neural networkstag:joss.theoj.org,2005:Paper/32542022-02-11T18:22:41Z2022-02-12T00:00:50ZTorchMetrics - Measuring Reproducibility in PyTorchacceptedv0.6.22021-12-17 08:21:43 UTC702022-02-11 18:22:41 UTC720224101NickiSkafteDetlefsenGrid AI Labs, Technical University of Denmark0000-0002-8133-682XJiriBorovecGrid AI Labs0000-0001-7437-824XJustusSchockGrid AI Labs, University Hospital Düsseldorf0000-0003-0512-3053AnanyaHarshJhaGrid AI LabsTeddyKokerGrid AI LabsLucaDi LielloUniversity of TrentoDanielStanclCharles UniversityChangshengQuanZhejiang UniversityMaximGrechkinIndependent ResearcherWilliamFalconGrid AI Labs, New York University10.21105/joss.04101https://doi.org/10.5281/zenodo.6037875Pythonhttps://joss.theoj.org/papers/10.21105/joss.04101.pdfpython, deep learning, pytorchtag:joss.theoj.org,2005:Paper/31042022-01-29T01:00:18Z2022-01-30T19:09:58ZDelve: Neural Network Feature Variance Analysisacceptedv0.1.482021-10-08 17:58:31 UTC692022-01-29 01:00:18 UTC720223992JustinShenkVisioLab, Berlin, Germany, Institute of Cognitive Science, University of Osnabrueck, Osnabrueck, Germany0000-0002-0664-7337MatsL.RichterInstitute of Cognitive Science, University of Osnabrueck, Osnabrueck, Germany0000-0002-9525-9730WolfByttnerRapid Health, London, England, United Kingdom0000-0002-9525-973010.21105/joss.03992https://doi.org/10.5281/zenodo.5865465Pythonhttps://joss.theoj.org/papers/10.21105/joss.03992.pdfdeep learning, machine learning, saturation, pytorch, AItag:joss.theoj.org,2005:Paper/31142021-12-13T17:08:35Z2021-12-21T10:36:39ZflowTorch - a Python library for analysis and reduced-order modeling of fluid flowsacceptedv1.02021-10-18 13:47:35 UTC682021-12-13 17:08:35 UTC620213860AndreWeinerTechnische Universität Braunschweig, Institute of Fluid Mechanics, Flow Modeling and Control Group0000-0001-5617-1560RichardSemaanTechnische Universität Braunschweig, Institute of Fluid Mechanics, Flow Modeling and Control Group0000-0002-3219-054510.21105/joss.03860https://doi.org/10.5281/zenodo.5770244Python, C++https://joss.theoj.org/papers/10.21105/joss.03860.pdfPyTorch, fluid flows, reduced-order modeling, modal analysistag:joss.theoj.org,2005:Paper/27642021-08-31T16:32:55Z2021-09-01T14:03:51Ztorchquad: Numerical Integration in Arbitrary Dimensions with PyTorchacceptedv0.2.12021-06-15 15:02:24 UTC642021-08-31 16:32:55 UTC620213439PabloGómezAdvanced Concepts Team, European Space Agency, Noordwijk, The Netherlands0000-0002-5631-8240HåvardHemToftevaagAdvanced Concepts Team, European Space Agency, Noordwijk, The Netherlands0000-0003-4692-5722GabrieleMeoniAdvanced Concepts Team, European Space Agency, Noordwijk, The Netherlands0000-0001-9311-639210.21105/joss.03439https://doi.org/10.5281/zenodo.5344938Pythonhttps://joss.theoj.org/papers/10.21105/joss.03439.pdfn-dimensional, numerical integration, GPU, automatic differentiation, PyTorch, high-performance computing, machine learningtag:joss.theoj.org,2005:Paper/20672020-10-19T20:52:07Z2021-02-15T11:29:52Zpystiche: A Framework for Neural Style Transferacceptedv0.6.12020-10-08 18:39:49 UTC542020-10-19 20:52:07 UTC520202761PhilipMeierinIT –- Institute Industrial IT, Technische Hochschule Ostwestfalen-Lippe (TH-OWL)0000-0002-5184-1622VolkerLohweginIT –- Institute Industrial IT, Technische Hochschule Ostwestfalen-Lippe (TH-OWL)0000-0002-3325-788710.21105/joss.02761https://doi.org/10.5281/zenodo.4107044Pythonhttps://joss.theoj.org/papers/10.21105/joss.02761.pdfNeural Style Transfer, framework, PyTorchtag:joss.theoj.org,2005:Paper/19372020-09-27T10:49:02Z2021-02-15T11:30:09ZFoolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAXacceptedv3.1.02020-08-10 18:30:38 UTC532020-09-27 10:49:02 UTC520202607JonasRauberTübingen AI Center, University of Tübingen, Germany, International Max Planck Research School for Intelligent Systems, Tübingen, Germany0000-0001-6795-9441RolandZimmermannTübingen AI Center, University of Tübingen, Germany, International Max Planck Research School for Intelligent Systems, Tübingen, GermanyMatthiasBethgeTübingen AI Center, University of Tübingen, Germany, Bernstein Center for Computational Neuroscience Tübingen, GermanyWielandBrendelTübingen AI Center, University of Tübingen, Germany, Bernstein Center for Computational Neuroscience Tübingen, Germany10.21105/joss.02607https://doi.org/10.5281/zenodo.4050932Python, JavaScript, Jupyter Notebookhttps://joss.theoj.org/papers/10.21105/joss.02607.pdfpython, machine learning, adversarial attacks, neural networks, pytorch, tensorflow, jax, keras, eagerpytag:joss.theoj.org,2005:Paper/11592019-09-02T00:00:00Z2021-02-15T11:31:47ZdeepCR: Cosmic Ray Rejection with Deep Learningaccepted0.1.52019-08-13 20:53:31 UTC412019-09-02 00:00:00 UTC420191651KemingZhangDepartment of Astronomy, University of California, Berkeley0000-0002-9870-5695JoshuaS.BloomDepartment of Astronomy, University of California, Berkeley, Lawrence Berkeley National Laboratory0000-0002-7777-216X10.21105/joss.01651https://doi.org/10.5281/zenodo.3383309Pythonhttps://joss.theoj.org/papers/10.21105/joss.01651.pdfPytorch, astronomy, image processing, cosmic ray, deep learning