1 dépôt
A utility that analyzes neural network graphs to remove redundant parameters and accelerate model execution.
Distinct from Model Pruning: Distinct from Model Pruning: focuses on the tool implementation aspect for graph analysis and automated parameter removal rather than general pruning concepts.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Deep Learning Pruning Toolkits. Refine with filters or upvote what's useful.
Torch-Pruning is a deep learning model pruning tool and neural network optimization toolkit designed for PyTorch. The library analyzes neural network graphs to remove redundant parameters and channels, reducing model size and computational costs. The framework traces computational graphs dynamically using sample inputs to map relational dependencies and identify coupled layers that require simultaneous pruning. It evaluates and ranks layer parameters across the entire network using global importance ranking and applies structural constraints to optimize overall outcomes. Additional capabili
A utility that analyzes neural network graphs to remove redundant parameters and accelerate model execution.