h1

% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@MASTERSTHESIS{Mainka:1009964,
      author       = {Mainka, Irmin},
      othercontributors = {Müller, Matthias S. and Kunkel, Julian and Viehhauser,
                          Dominik},
      title        = {{E}valuierung von {O}ptimierungsstrategien zur
                      {D}atensatzspeicherung für machinelles {L}ernen auf {HPC}
                      {S}ystemen},
      school       = {RWTH Aachen University},
      type         = {Bachelorarbeit},
      address      = {Aachen},
      publisher    = {RWTH Aachen University},
      reportid     = {RWTH-2025-03758},
      pages        = {1 Online-Ressource : Illustrationen},
      year         = {2025},
      note         = {Veröffentlicht auf dem Publikationsserver der RWTH Aachen
                      University; Bachelorarbeit, RWTH Aachen University, 2025},
      abstract     = {Traditional Machine Learning Datasets used to train models
                      are often used in aform consisting of a large amount of
                      small files. This property is detrimental totheir widespread
                      use on HPC systems due to the way parallel filesystems
                      work.Several other ways to store such datasets can be found
                      in the areas of both HPCand Python programming. Strategies
                      for both storing and loading datasets aretested in
                      experiments in this thesis. These experiments focus on
                      training an ImageClassification model. The strategies used
                      in this thesis include the usage of numpyarrays, LMDB, HDF5
                      and Zarr. The results are then used to evaluate how
                      thedifferent strategies compare to each other. The goal of
                      this thesis is to either finda performant strategy using
                      fewer files or validate the usage of the strategy usingmany
                      small files.},
      cin          = {123010 / 022000 / 120000},
      ddc          = {004},
      cid          = {$I:(DE-82)123010_20140620$ / $I:(DE-82)022000_20140101$ /
                      $I:(DE-82)120000_20140620$},
      typ          = {PUB:(DE-HGF)2},
      doi          = {10.18154/RWTH-2025-03758},
      url          = {https://publications.rwth-aachen.de/record/1009964},
}