training food-101 (achieved SOTA top-1 validation acc ~=90%) using 1-cycle-policy:
-
Updated
Aug 24, 2019 - Jupyter Notebook
#
learning-rate-finder
Here are 7 public repositories matching this topic...
Pytorch implementation of arbitrary learning rate and momentum schedules, including the One Cycle Policy
-
Updated
Jul 15, 2020 - Python
Experiments comparing keras and fastai implementations of the learning rate finder.
-
Updated
Mar 24, 2023 - Jupyter Notebook
Classify footware based on closures : https://nbviewer.jupyter.org/github/shubhajitml/footware/tree/master/
-
Updated
Aug 18, 2019 - Jupyter Notebook
Implementation of some new techniques from fastai and other papers which works with keras models
-
Updated
Dec 26, 2018 - Python
Experiments on the paper Super-Convergence
-
Updated
Jan 6, 2020 - Jupyter Notebook
set of algorithms that I have implemented for some random projects
python algorithms optimization rpca learning-rate-finder robust-principal-component-analysis augmented-lagrange-multipliers
-
Updated
Aug 17, 2019 - Jupyter Notebook
Improve this page
Add a description, image, and links to the learning-rate-finder topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the learning-rate-finder topic, visit your repo's landing page and select "manage topics."