A Closer Look at Structured Pruning for Neural Network Compression

Overview

A Closer Look at Structured Pruning for Neural Network Compression

Code used to reproduce experiments in https://arxiv.org/abs/1810.04622.

To prune, we fill our networks with custom MaskBlocks, which are manipulated using Pruner in funcs.py. There will certainly be a better way to do this, but we leave this as an exercise to someone who can code much better than we can.

Setup

This is best done in a clean conda environment:

conda create -n prunes python=3.6
conda activate prunes
conda install pytorch torchvision -c pytorch

Repository layout

-train.py: contains all of the code for training large models from scratch and for training pruned models from scratch
-prune.py: contains the code for pruning trained models
-funcs.py: contains useful pruning functions and any functions we used commonly

CIFAR Experiments

First, you will need some initial models.

To train a WRN-40-2:

python train.py --net='res' --depth=40 --width=2.0 --data_loc= --save_file='res'

The default arguments of train.py are suitable for training WRNs. The following trains a DenseNet-BC-100 (k=12) with its default hyperparameters:

python train.py --net='dense' --depth=100 --data_loc= --save_file='dense' --no_epochs 300 -b 64 --epoch_step '[150,225]' --weight_decay 0.0001 --lr_decay_ratio 0.1

These will automatically save checkpoints to the checkpoints folder.

Pruning

Once training is finished, we can prune our networks using prune.py (defaults are set to WRN pruning, so extra arguments are needed for DenseNets)

python prune.py --net='res'   --data_loc= --base_model='res' --save_file='res_fisher'
python prune.py --net='res'   --data_loc= --l1_prune=True --base_model='res' --save_file='res_l1'

python prune.py --net='dense' --depth 100 --data_loc= --base_model='dense' --save_file='dense_fisher' --learning_rate 1e-3 --weight_decay 1e-4 --batch_size 64 --no_epochs 2600
python prune.py --net='dense' --depth 100 --data_loc= --l1_prune=True --base_model='dense' --save_file='dense_l1'  --learning_rate 1e-3 --weight_decay 1e-4 --batch_size 64  --no_epochs 2600

Note that the default is to perform Fisher pruning, so you don't need to pass a flag to use it.
Once finished, we can train the pruned models from scratch, e.g.:

python train.py --data_loc= --net='res' --base_file='res_fisher__prunes' --deploy --mask=1 --save_file='res_fisher__prunes_scratch'

Each model can then be evaluated using:

python train.py --deploy --eval --data_loc= --net='res' --mask=1 --base_file='res_fisher__prunes'

Training Reduced models

This can be done by varying the input arguments to train.py. To reduce depth or width of a WRN, change the corresponding option:

python train.py --net='res' --depth= --width= --data_loc= --save_file='res_reduced'

To add bottlenecks, use the following:

python train.py --net='res' --depth=40 --width=2.0 --data_loc= --save_file='res_bottle' --bottle --bottle_mult 

With DenseNets you can modify the depth or growth, or use --bottle --bottle_mult as above.

Acknowledgements

Jack Turner wrote the L1 stuff, and some other stuff for that matter.

Code has been liberally borrowed from many a repo, including, but not limited to:

https://github.com/xternalz/WideResNet-pytorch
https://github.com/bamos/densenet.pytorch
https://github.com/kuangliu/pytorch-cifar
https://github.com/ShichenLiu/CondenseNet

Citing this work

If you would like to cite this work, please use the following bibtex entry:

@article{crowley2018pruning,
  title={A Closer Look at Structured Pruning for Neural Network Compression},
  author={Crowley, Elliot J and Turner, Jack and Storkey, Amos and O'Boyle, Michael},
  journal={arXiv preprint arXiv:1810.04622},
  year={2018},
  }
Owner
Bayesian and Neural Systems Group
Machine learning research group @ University of Edinburgh
Bayesian and Neural Systems Group
StocksMA is a package to facilitate access to financial and economic data of Moroccan stocks.

Creating easier access to the Moroccan stock market data What is StocksMA ? StocksMA is a package to facilitate access to financial and economic data

Salah Eddine LABIAD 28 Jan 04, 2023
Code for ICCV 2021 paper "Distilling Holistic Knowledge with Graph Neural Networks"

HKD Code for ICCV 2021 paper "Distilling Holistic Knowledge with Graph Neural Networks" cifia-100 result The implementation of compared methods are ba

Wang Yucheng 30 Dec 18, 2022
Graph Neural Networks with Keras and Tensorflow 2.

Welcome to Spektral Spektral is a Python library for graph deep learning, based on the Keras API and TensorFlow 2. The main goal of this project is to

Daniele Grattarola 2.2k Jan 08, 2023
Official implementation of Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

Deep-Rep-MFIR Official implementation of Deep Reparametrization of Multi-Frame Super-Resolution and Denoising Publication: Deep Reparametrization of M

Goutam Bhat 39 Jan 04, 2023
Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

Awesome Visual-Transformer Collect some Transformer with Computer-Vision (CV) papers. If you find some overlooked papers, please open issues or pull r

dkliang 2.8k Jan 08, 2023
Unsupervised phone and word segmentation using dynamic programming on self-supervised VQ features.

Unsupervised Phone and Word Segmentation using Vector-Quantized Neural Networks Overview Unsupervised phone and word segmentation on speech data is pe

Herman Kamper 13 Dec 11, 2022
MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions

MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions Project Page | Paper If you find our work useful for your research, please con

96 Jan 04, 2023
Code for our TKDE paper "Understanding WeChat User Preferences and “Wow” Diffusion"

wechat-wow-analysis Understanding WeChat User Preferences and “Wow” Diffusion. Fanjin Zhang, Jie Tang, Xueyi Liu, Zhenyu Hou, Yuxiao Dong, Jing Zhang,

18 Sep 16, 2022
CVPR '21: In the light of feature distributions: Moment matching for Neural Style Transfer

In the light of feature distributions: Moment matching for Neural Style Transfer (CVPR 2021) This repository provides code to recreate results present

Nikolai Kalischek 49 Oct 13, 2022
Out-of-Town Recommendation with Travel Intention Modeling (AAAI2021)

TrainOR_AAAI21 This is the official implementation of our AAAI'21 paper: Haoran Xin, Xinjiang Lu, Tong Xu, Hao Liu, Jingjing Gu, Dejing Dou, Hui Xiong

Jack Xin 13 Oct 19, 2022
Learning Visual Words for Weakly-Supervised Semantic Segmentation

[IJCAI 2021] Learning Visual Words for Weakly-Supervised Semantic Segmentation Implementation of IJCAI 2021 paper Learning Visual Words for Weakly-Sup

Lixiang Ru 24 Oct 05, 2022
Official source code to CVPR'20 paper, "When2com: Multi-Agent Perception via Communication Graph Grouping"

When2com: Multi-Agent Perception via Communication Graph Grouping This is the PyTorch implementation of our paper: When2com: Multi-Agent Perception vi

34 Nov 09, 2022
Novel and high-performance medical image classification pipelines are heavily utilizing ensemble learning strategies

An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networks Novel and high-performance medical ima

14 Dec 18, 2022
Collective Multi-type Entity Alignment Between Knowledge Graphs (WWW'20)

CG-MuAlign A reference implementation for "Collective Multi-type Entity Alignment Between Knowledge Graphs", published in WWW 2020. If you find our pa

Bran Zhu 28 Dec 11, 2022
This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"

This is an official pytorch implementation of ActionCLIP: A New Paradigm for Video Action Recognition [arXiv] Overview Content Prerequisites Data Prep

268 Jan 09, 2023
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

EFENet EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation Code is a bit messy now. I woud clean up soon. For training the EF

Yaping Zhao 19 Nov 05, 2022
Official code for our EMNLP2021 Outstanding Paper MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks

MindCraft Authors: Cristian-Paul Bara*, Sky CH-Wang*, Joyce Chai This is the official code repository for the paper (arXiv link): Cristian-Paul Bara,

Situated Language and Embodied Dialogue (SLED) Research Group 14 Dec 29, 2022
Simple-Image-Classification - Simple Image Classification Code (PyTorch)

Simple-Image-Classification Simple Image Classification Code (PyTorch) Yechan Kim This repository contains: Python3 / Pytorch code for multi-class ima

Yechan Kim 8 Oct 29, 2022
CVPR 2020 oral paper: Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax.

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax ⚠️ Latest: Current repo is a complete version. But we delet

FishYuLi 341 Dec 23, 2022
A TensorFlow 2.x implementation of Masked Autoencoders Are Scalable Vision Learners

Masked Autoencoders Are Scalable Vision Learners A TensorFlow implementation of Masked Autoencoders Are Scalable Vision Learners [1]. Our implementati

Aritra Roy Gosthipaty 59 Dec 10, 2022