Skip to content
/ pruning Public

Implementation of post-hoc weight pruning for sparse neural networks.

Notifications You must be signed in to change notification settings

ninkle/pruning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pruning

To build and run:

Ensure that you have TensorFlow installed on your machine.

Run commands:
pip3 install -e .
cd pruning

To train model from scratch and evaluate pruned networks, run:
python run.py run

To load pre-trained model and evaluate pruned networks, run:
python run.py run --load-trained

To see results and analysis, open experiments.ipynb.

About

Implementation of post-hoc weight pruning for sparse neural networks.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published