David Schischke's repositories
carbontracker
Track and predict the energy consumption and carbon footprint of training deep learning models.
convolution_visualisation
A simple Visualisation of Convolution Activations using LeNet5 and MNIST Data
daaawit.github.io
Pages
data-science-project-template
The HSG Data Science Project Template is a cookiecutter template to configure data science project repositories.
GraSP
Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH
incompletedata_research_case_study
Simulation study for Statistical Analysis of Incomplete Data Winter 2021/2022
itsp
Introduction to Speech Processing
prospr
Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients
snip
Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.
unstructured_pruning_at_init
Evaluation of Efficiency of Unstructured Pruning at Initialization