[CVPR 2023] DepGraph: Towards Any Structural Pruning

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

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

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.

A simple and effective LLM pruning approach.

Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019), "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020) and “Manifold Regularized Dynamic Network Pruning” (CVPR 2021).

Efficient Sparse-Winograd Convolutional Neural Networks (ICLR 2018)

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

SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY

[ICLR 2020]: 'AtomNAS: Fine-Grained End-to-End Neural Architecture Search'

Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934

(CVPR 2021, Oral) Dynamic Slimmable Network

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

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

[NeurIPS 2023] Structural Pruning for Diffusion Models

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

CAE-ADMM: Implicit Bitrate Optimization via ADMM-Based Pruning in Compressive Autoencoders

Knowledge distillation from Ensembles of Iterative pruning (BMVC 2020)

Tensorflow codes for "Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers"

Lookahead: A Far-sighted Alternative of Magnitude-based Pruning (ICLR 2020)