This repository is the official implementation of the paper Pruning via Iterative Ranking of Sensitivity Statistics and implements novel pruning / compression algorithms for deep learning / neural networks. Amongst others it implements structured pruning before training, its actual parameter shrinking and unstructured before/during training.
science machine-learning computer-vision deep-learning artificial-intelligence neural-networks pruning publication speedup science-research model-compression structured-pruning unstructured-pruning structured-pruning-before-training
-
Updated
May 22, 2023 - Python