1167 research outputs found
Sort by
Analysis of convolutional neural network image classifiers in a rotationally symmetric model: Implementations of the estimates and links to image data sets
No full textThis repository contains the Python code required to reproduce the simulation part of the paper "Analysis of convolutional neural network image classifiers in a rotationally symmetric model" from Kohler and Walter (2023) referenced below. The Python version used is Python 3.9.7. This work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under project number 449102119. The mnist-rot image dataset consisting of the real images from which the classes "four" and "nine" were used can be downloaded from the link given below. The paper by Larochelle et al. (2007) linked below describes the dataset in more detail. The link for the original mnist dataset has also been linked below
A residual-based non-orthogonality correction for force-balanced unstructured Volume-of-Fluid methods - codes
No full textA residual-based non-orthogonality correction for force-balanced unstructured Volume-of-Fluid methods - code
2023_Sos-Bruder_MaterDes_AlSi10Mg-lattices
No full textResearch and raw data to publication: Sos M, Meyer G, Durst K, Mittelstedt C, Bruder E. Microstructure and mechanical properties of additively manufactured AlSi10Mg lattice structures from single contour exposure. Materials & Design. 2023;227:111796. https://doi.org/10.1016/j.matdes.2023.11179
Numerical Wetting Benchmarks - Advancing the plicRDF-isoAdvector unstructured Volume-of-Fluid (VOF) method using the RDF curvature model- Jupyter Notebooks, CSV files, Secondary Data, Parameter variation file
No full textJupyter notebooks for post-processing of the wetting benchmark results using RDF curvature model. The post-processing, based on Jupyter notebooks, are not just for OpenFOAM, but for any other simulation software provided the files storing the secondary data (error norms) are organized as described in the README.md file.Firs
SIS18 Machine Experiment: Identification of Magnetic Field Errors using the DLMN Approach
No full textExperiment intended to demonstrate the DLMN approach to identify non-linear magnetic field errors in particle accelerators
CRC 1194 guideline on linking research data with publications
Get PDFThe goal of the guideline is to support FAIR principles in research with concrete steps that each researcher can perform to increase the Findability, Accessibility, Interoperability and Reproducibility of their research.1.
Classification of gravure printed patterns using convolutional neural networks (Python code)
No full textThis dataset contains Python code ('code_DeepLearn_ImgClass.zip') for
automated classification of gravure printed patterns from the
[HYPA-p](https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/3841) dataset.
The developed algorithm performs supervised deep learning of convolutional
neural networks (CNNs) on labeled data ('CNN_dataset.zip'), i.e. selected,
labeled 'S-subfields' from the HYPA-p dataset. 'CNN_dataset.zip' is a subset
from the images in the folder 'labeled_data.zip', which can be created with
the provided Python code. PyTorch is used as a deep learning framework. The
Python code yields trained CNNs, which can be used for automated
classification of unlabeled data from the HYPA-p dataset.
Well-known, pre-trained network architectures like Densenet-161 or MobileNetV2
are used as a starting point for training. Several trained CNNs are included
in this submission, see 'trained_CNN_models.zip'.
Further information can be found in the dissertation of Pauline Rothmann-Brumm
(2023) and in the provided README-file
Darmstadt engine flow bench velocity data
No full textThis set contains the experimental velocity data of the Darmstadt engine air flow bench for validation. The scaling, mean velocity, and standard deviation are included
Numerical Wetting Benchmarks - Advancing the plicRDF-isoAdvector unstructured Volume-of-Fluid (VOF) method using height-function curvature model- Jupyter Notebooks, CSV files, Secondary Data, Parameter variation file
No full textJupyter notebooks for post-processing of the wetting benchmark results. The post-processing, based on Jupyter notebooks, are not just for OpenFOAM, but for any other simulation software provided the files storing the secondary data (error norms) are organized as described in the README.md file.Firs