DOE OSTI · code-168795
network-pruner (Neural network pruning analysis) [SWR-25-113]
Abstract
This repository implements an iterative magnitude pruning algorithm for pruning neural networks in PyTorch. The pruning method involves gradually removing less significant weights from the model to achieve a specified sparsity, followed by fine-tuning the pruned model to recover performance.
Keep this discovery
Explore connections, maps & timelines
Griffin, Kevin [National Renewable Energy Laboratory (NREL), Golden, CO (United States)], Gafur, Jamil [National Renewable Energy Laboratory (NREL), Golden, CO (United States)], Milkert, Max [National Renewable Energy Laboratory (NREL), Golden, CO (United States)], Wimer, Nicholas [National Renewable Energy Laboratory (NREL), Golden, CO (United States)]. 2025-09-22. network-pruner (Neural network pruning analysis) [SWR-25-113]. https://doi.org/10.11578/dc.20251105.3
Cite the original work for its findings. Save a collection to share your selection of sources.