43 repository-uri
Awesome GitHub RepositoriesWeight Pruning
Techniques for removing individual neural network connections or parameters to reduce model size.
Explore 43 awesome GitHub repositories matching part of an awesome list · Weight Pruning. Refine with filters or upvote what's useful.
Awesome Weight Pruning GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- tencent/pocketflow
Tencent/PocketFlow
2,914Vezi pe GitHubPocketFlow is an integrated toolkit for deep learning model compression, distributed training, and mobile format optimization. It provides a system for reducing the size and complexity of neural networks to improve inference efficiency, featuring a dedicated engine for knowledge distillation and a mobile model optimizer. The framework differentiates itself through an automated hyperparameter tuning system that uses reinforcement learning and statistical models to determine optimal compression ratios and layer-wise bit allocation. It also includes a distributed training system that utilizes mu
Provides weight sparsification through a dynamic pruning schedule during training to reduce model size.
Pythonautomlcomputer-visiondeep-learning - robustbench/robustbench
RobustBench/robustbench
Francesco Croce\ (University of Tübingen), Maksym Andriushchenko\ (EPFL), Vikash Sehwag\ (Princeton University), Nicolas Flammarion (EPFL), Mung Chiang (Purdue University), Prateek Mittal (Princeton University), Matthias Hein (University of Tübingen)
Improving out-of-distribution robustness via network compression.
Python - google-research/lottery-ticket-hypothesis
google-research/lottery-ticket-hypothesis
This codebase was developed by Jonathan Frankle and David Bieber at Google during the summer of 2018.
Foundational lottery ticket hypothesis for sparse training.
Python - songhan/deep-compression-alexnet
songhan/Deep-Compression-AlexNet
March 15, 2019: for our most updated work on model compression and acceleration, please reference:
Foundational deep compression via pruning and quantization.
Python - jack-willturner/deepcompression-pytorch
jack-willturner/DeepCompression-PyTorch
A PyTorch implementation of this paper.
Learning weights and connections for efficient neural networks.
Jupyter Notebook - uber-research/deconstructing-lottery-tickets
uber-research/deconstructing-lottery-tickets
Hattie Zhou, Janice Lan, Rosanne Liu, Jason Yosinski
Deconstructing lottery tickets via zeros, signs, and supermasks.
Python - ist-daslab/obc
IST-DASLab/OBC
Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".
Framework for accurate post-training quantization and weight pruning.
Python - namhoonlee/snip-public
namhoonlee/snip-public
This repository contains code for the paper SNIP: Single-shot Network Pruning based on Connection Sensitivity (ICLR 2019).
Single-shot network pruning based on connection sensitivity.
Python - kaiqizhang/admm-pruning
KaiqiZhang/admm-pruning
Prune DNN using Alternating Direction Method of Multipliers (ADMM)
Systematic weight pruning framework using ADMM.
Python - yeshaokai/robustness-aware-pruning-admm
yeshaokai/Robustness-Aware-Pruning-ADMM
Adversarial Robustness vs Model Compression, or Both?
Adversarial robustness-aware pruning using ADMM.
Python - inspire-group/hydra
inspire-group/hydra
Repository with code to reproduce the results and checkpoints for compressed networks in our paper on novel pruning techniques with robust training. This repository supports all four robust training objectives: iterative adversarial training, randomized smoothing, MixTrain, and CROWN-IBP.
Pruning techniques for adversarially robust neural networks.
Python - jaeho-lee/layer-adaptive-sparsity
jaeho-lee/layer-adaptive-sparsity
This is the official implementation of the paper: "Layerwise Sparsity for Magnitude-based Pruning", ICLR 2021.
Magnitude-based pruning with layer-adaptive sparsity constraints.
Python - chrundle/biprop
chrundle/biprop
This method identifies a binary weight or binary weight and activation subnetwork within a randomly initialized network that achieves performance comparable to, and sometimes better than, a weight-optimized network. The resulting binarized and pruned networks that achieve comparable performance…
Finding binary neural networks via random network pruning.
Python - ososos888/prune-then-distill
ososos888/prune-then-distill
This is an PyTorch implement of the paper ``Prune Your Model Before Distill It''.
Combining pruning and distillation for efficient model compression.
Python - dingxiaoh/gsm-sgd
DingXiaoH/GSM-SGD
This repository contains the codes for the following NeurIPS-2019 paper
Global sparse momentum SGD for pruning deep networks.
Python - jingtongsu/sanity-checking-pruning
JingtongSu/sanity-checking-pruning
This repository contains the code for reproducing the results in the following paper:
Sanity checking pruning methods using random tickets.
Python - vita-group/sparsity-win-robust-generalization
VITA-Group/Sparsity-Win-Robust-Generalization
Code for the paper: ICLR 2022 Sparsity Winning Twice: Better Robust Generalization From More Efficient Training
Improving robust generalization through efficient sparse training.
Python - ganguli-lab/degrees-of-freedom
ganguli-lab/degrees-of-freedom
This repository contains source code for the ICLR 2022 paper How many degrees of freedom do we need to train deep networks: a loss landscape perspective by Brett W. Larsen, Sanislav Fort, Nic Becker, and Surya Ganguli (arXiv version).
Loss landscape perspective on required degrees of freedom.
Python - vita-group/sfw-once-for-all-pruning
VITA-Group/SFW-Once-for-All-Pruning
Code used for paper: ICLR 2022 Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, and No Retraining.
One-shot pruning using Frank-Wolfe optimization without retraining.
Python - yueb17/dlth
yueb17/DLTH
This repository is for our ICLR'22 paper:
Dual lottery ticket hypothesis for sparse network training.
Python
