Awesome Pruning. ✅ Curated Resources for Neural Network Pruning.

3rd place solution for NeurIPS 2019 MicroNet challenge

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.

Knowledge distillation from Ensembles of Iterative pruning (BMVC 2020)

(Unstructured) Weight Pruning via Adaptive Sparsity Loss

Research-ready and production-friendly neural network pruning for PyTorch—transparent methods, reproducible baselines, and deployment metrics to compress models for real-world use.

Submission name: QualcommAI-EfficientNet. MicroNet Challenge (NeurIPS 2019) submission - Qualcomm AI Research

[Project] Structured/Unstructured Pruning Comparison Experiment

[Project] Edge computing What Makes a Good Prune? Comparison Experiment

ESPN: Extreme Sparse Pruned Network

Apply Simulated Annealing and Genetic Algorithm to solve the problem of Neural Network pruning without prior assumptions of weight importance

The repository contains an implementation to try experiments of Lottery Ticket Hypothesis