Skip to content

Experiments on the strong lottery ticket hypothesis for convolutional neural networks

License

Notifications You must be signed in to change notification settings

AInnervate/cnnslth

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Experiments on the strong lottery ticket hypothesis for convolutional neural networks

This is the code used to produce the empyrical results reported in our paper.

Running

All commands referred should be executed in the project's root directory.

A working installation of Gurobi Optimizer is necessary to run the experiments. To install the other dependencies, start Julia and run

using Pkg; Pkg.activate("."); Pkg.instantiate()

To perform the experiments and generate the plots, run

julia --project=. main.jl

The script will look for cached solutions in saves/. This search is based on file's names, so renaming them (or using different parameters) will generate solutions from scratch (which can take many hours).

About

Experiments on the strong lottery ticket hypothesis for convolutional neural networks

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages