DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments

Alberti, Michele; Pondenkandath, Vinaychandran; Gygli, Marcel; Ingold, Rolf; Liwicki, Marcus (8 August 2018). DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR) (pp. 423-428). New York: IEEE 10.1109/ICFHR-2018.2018.00080

Text DeepDIVA_A_Highly-Functional_Python_Framework_for_Reproducible_Experiments.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (541kB) | Request a copy

We introduce DeepDIVA: an infrastructure designed to enable quick and intuitive setup of reproducible experiments with a large range of useful analysis functionality. Reproducing scientific results can be a frustrating experience, not only in document image analysis but in machine learning in general. Using DeepDIVA a researcher can either reproduce a given experiment or share their own experiments with others. Moreover, the framework offers a large range of functions, such as boilerplate code, keeping track of experiments, hyper-parameter optimization, and visualization of data and results. To demonstrate the effectiveness of this framework, this paper presents case studies in the area of handwritten document analysis where researchers benefit from the integrated functionality. DeepDIVA is implemented in Python and uses the deep learning framework PyTorch. It is completely open source, and accessible as Web Service through DIVAServices.

Item Type:	Conference or Workshop Item (Paper)
Division/Institute:	Business School > Institute for Public Sector Transformation > Data and Infrastructure Business School
Name:	Alberti, Michele; Pondenkandath, Vinaychandran; Gygli, Marcel; Ingold, Rolf and Liwicki, Marcus
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
ISBN:	978-1-5386-5875-8
Publisher:	IEEE
Language:	English
Submitter:	Marcel Gygli
Date Deposited:	10 Oct 2023 15:55
Last Modified:	10 Oct 2023 15:55
Publisher DOI:	10.1109/ICFHR-2018.2018.00080
ARBOR DOI:	10.24451/arbor.20052
URI:	https://arbor.bfh.ch/id/eprint/20052