no code implementations • 22 Jun 2023 • Patrick Plagwitz, Frank Hannig, Jürgen Teich, Oliver Keszocze
Due to their compute- and data-intensive nature, CNN accelerators have been developed as ASICs or on FPGAs.
no code implementations • 29 Sep 2021 • Muhammad Sabih, Frank Hannig, Jürgen Teich
Our proposed architecture for dynamic pruning can be deployed on different hardware platforms.
no code implementations • 27 Jan 2021 • Frank Hannig, Paolo Meloni, Matteo Spallanzani, Matthias Ziegler
This volume contains the papers accepted at the first DATE Friday Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures (SLOHA 2021), held virtually on February 5, 2021.
no code implementations • 26 Aug 2020 • M. Akif Özkan, Burak Ok, Bo Qiao, Jürgen Teich, Frank Hannig
OpenVX promises to solve this issue for computer vision applications with a royalty-free industry standard that is based on a graph-execution model.
no code implementations • 20 Aug 2020 • Muhammad Sabih, Frank Hannig, Juergen Teich
We use these methods for (1) pruning of DNNs; this includes structured and unstructured pruning of \ac{CNN} filters pruning as well as pruning weights of fully connected layers, (2) non-uniform quantization of DNN weights using clustering algorithm; this is also referred to as Weight Sharing, and (3) integer-based mixed-precision quantization; this is where each layer of a DNN may use a different number of integer bits.
no code implementations • 26 Feb 2015 • Oliver Reiche, Konrad Häublein, Marc Reichenbach, Frank Hannig, Jürgen Teich, Dietmar Fey
Therefore, in previous work, we have shown that elevating the description of image algorithms to an even higher abstraction level, by using a Domain-Specific Language (DSL), can significantly cut down the complexity for designing such algorithms for FPGAs.
no code implementations • 25 Feb 2015 • Frank Hannig, Dietmar Fey, Anton Lokhmotov
This volume contains the papers accepted at the DATE Friday Workshop on Heterogeneous Architectures and Design Methods for Embedded Image Systems (HIS 2015), held in Grenoble, France, March 13, 2015.
no code implementations • 20 Aug 2014 • Moritz Schmid, Oliver Reiche, Christian Schmitt, Frank Hannig, Jürgen Teich
Multiresolution Analysis (MRA) is a mathematical method that is based on working on a problem at different scales.