-
University of Tübingen
- Tübingen
- aferro.dynu.net
Stars
Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)
Efficient PyTorch Hessian eigendecomposition tools!
Figure sizes, font sizes, fonts, and more configurations at minimal overhead. Fix your journal papers, conference proceedings, and other scientific publications.
PyTorch implementation of "Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer"
Code for Continuously Changing Corruptions (CCC) benchmark + evaluation
Sphinx extension for automatic generation of an example gallery
What's the probability of being hit by a satellite?
"Probabilistic Machine Learning" - a book series by Kevin Murphy
Source code for my PhD thesis: Backpropagation Beyond the Gradient
[TMLR 2022] Curvature access through the generalized Gauss-Newton's low-rank structure: Eigenvalues, eigenvectors, directional derivatives & Newton steps
Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations
Flet enables developers to easily build realtime web, mobile and desktop apps in Python. No frontend experience required.
Machine learning course materials.
LaTeX template for my PhD thesis at the University of Tuebingen
AudioLDM: Generate speech, sound effects, music and beyond, with text.
Tutorial materials of the Probabilistic Numerics Spring School.
Common Music bindings for the Common Lisp version of the Fomus music notation processor. See cm and fomus repos here.
PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)
A playbook for systematically maximizing the performance of deep learning models.
FizzBuzz Enterprise Edition is a no-nonsense implementation of FizzBuzz made by serious businessmen for serious business purposes.
Deep face segmentation in extremely hard conditions
End-to-end, automatic face swapping pipeline
Code accompanying the NeurIPS 2021 Paper: A Probabilistic State Space Model for Joint Inference from Differential Equations and Data (Schmidt, Krämer, Hennig)
[MLSys 2022] "BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling" by Cheng Wan, Youjie Li, Ang Li, Nam Sung Kim, Yin…
[ICLR 2021 Spotlight] "CPT: Efficient Deep Neural Network Training via Cyclic Precision" by Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, and Yingyan (Celine) Lin.