🧠 Singular values-driven automated filter pruning

Make Structured Pruning Methods Smooth and Adaptive: Decay Pruning Method (DPM) is a novel smooth and dynamic pruning approach, that can be seemingly integrated with various existing structured pruning methods, providing significant improvement.

[CVPR 2023] DepGraph: Towards Any Structural Pruning

Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning, IEEE Transactions on Knowledge and Data Engineering 2024

Collection of recent methods on (deep) neural network compression and acceleration.

A simple and effective LLM pruning approach.

[TPAMI 2023, NeurIPS 2020] Code release for "Deep Multimodal Fusion by Channel Exchanging"

[NeurIPS 2023] Structural Pruning for Diffusion Models

💍 Efficient tensor decomposition-based filter pruning

[TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

Reimplementation of Sparse Variational Dropout in Keras-Core/Keras 3.0

This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" by Jonathan Frankle and Michael Carbin that can be easily adapted to any model/dataset.

Network Pruning

[ICLR'23] Trainability Preserving Neural Pruning (PyTorch)

In this repository using the sparse training, group channel pruning and knowledge distilling for YOLOV4,

[T-PAMI'23] PAGCP for the compression of YOLOv5

[Preprint] Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning

Counting currency from video using RepNet as a base model.

The official code for our ACCV2022 poster paper: Network Pruning via Feature Shift Minimization.

Code for the project "SNIP: Single-Shot Network Pruning"