Skip to content

dmarcosg/ScaleEqNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ScaleEqNet, Scale equavariant CNNs with vector fields

Implementation of the method it: Scale equivariance in CNNs with vector fields (ICML Workshops 2018), D Marcos, B Kellenberger, S Lobry, D Tuia https://arxiv.org/pdf/1807.11783.pdf

Implementation based on the work of Anders U. Waldeland https://github.com/COGMAR/RotEqNet/

Usage

To download and setup the MNIST-scale dataset, cd into the mnist folder and run:

python download_mnist.py
python make_mnist_scale.py

To run the MNIST-scale test:

python mnist_test.py

This code has been tested with Python 3.6.

The following python packages are required:

torch
numpy
scipy

About

Scale equavariant CNNs with vector fields

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages