1 रिपॉजिटरी
Reducing the size of deep learning models by removing unnecessary parameters and channels to lower memory and compute costs.
Distinct from Convolutional Channel Pruning: Distinct from Convolutional Channel Pruning: covers broader structural pruning of neural network parameters and channels beyond strictly convolutional layers.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Structured Neural Network Pruning. 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
Reducing the size of deep learning models by removing unnecessary parameters and channels to lower memory and compute costs.