Codes and models of NeurIPS2021 paper - DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

Overview

DominoSearch

This is repository for codes and models of NeurIPS2021 paper - DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

Instructions and other materials will be released soon.

Search:

git clone https://github.com/NM-sparsity/DominoSearch.git
cd DominoSearch/DominoSearch/search/script_resnet_ImageNet

We provide several search scripts for different sparse-ratio target, you can specify your own target and change the parameters accordingly. Note, you need to first specify your ImageNet dataset path

The searching phase could take 2-3 hours, then you will get searched schemes stored in a txt file, which will be needed as input for mixed-sparsity training.

Below is an example of output formate.

{'SparseConv0_3-64-(7, 7)': [16, 16], 'SparseConv1_64-64-(1, 1)': [16, 16], 'SparseConv2_64-64-(3, 3)': [4, 16], 'SparseConv3_64-256-(1, 1)': [8, 16], 'SparseConv4_64-256-(1, 1)': [8, 16], 'SparseConv5_256-64-(1, 1)': [8, 16], 'SparseConv6_64-64-(3, 3)': [4, 16], 'SparseConv7_64-256-(1, 1)': [8, 16], 'SparseConv8_256-64-(1, 1)': [8, 16], 'SparseConv9_64-64-(3, 3)': [4, 16], 'SparseConv10_64-256-(1, 1)': [8, 16], 'SparseConv11_256-128-(1, 1)': [8, 16], 'SparseConv12_128-128-(3, 3)': [2, 16], 'SparseConv13_128-512-(1, 1)': [8, 16], 'SparseConv14_256-512-(1, 1)': [4, 16], 'SparseConv15_512-128-(1, 1)': [8, 16], 'SparseConv16_128-128-(3, 3)': [4, 16], 'SparseConv17_128-512-(1, 1)': [8, 16], 'SparseConv18_512-128-(1, 1)': [8, 16], 'SparseConv19_128-128-(3, 3)': [4, 16], 'SparseConv20_128-512-(1, 1)': [8, 16], 'SparseConv21_512-128-(1, 1)': [8, 16], 'SparseConv22_128-128-(3, 3)': [2, 16], 'SparseConv23_128-512-(1, 1)': [8, 16], 'SparseConv24_512-256-(1, 1)': [4, 16], 'SparseConv25_256-256-(3, 3)': [2, 16], 'SparseConv26_256-1024-(1, 1)': [4, 16], 'SparseConv27_512-1024-(1, 1)': [4, 16], 'SparseConv28_1024-256-(1, 1)': [4, 16], 'SparseConv29_256-256-(3, 3)': [2, 16], 'SparseConv30_256-1024-(1, 1)': [4, 16], 'SparseConv31_1024-256-(1, 1)': [4, 16], 'SparseConv32_256-256-(3, 3)': [2, 16], 'SparseConv33_256-1024-(1, 1)': [4, 16], 'SparseConv34_1024-256-(1, 1)': [4, 16], 'SparseConv35_256-256-(3, 3)': [2, 16], 'SparseConv36_256-1024-(1, 1)': [4, 16], 'SparseConv37_1024-256-(1, 1)': [4, 16], 'SparseConv38_256-256-(3, 3)': [2, 16], 'SparseConv39_256-1024-(1, 1)': [4, 16], 'SparseConv40_1024-256-(1, 1)': [4, 16], 'SparseConv41_256-256-(3, 3)': [2, 16], 'SparseConv42_256-1024-(1, 1)': [4, 16], 'SparseConv43_1024-512-(1, 1)': [4, 16], 'SparseConv44_512-512-(3, 3)': [2, 16], 'SparseConv45_512-2048-(1, 1)': [4, 16], 'SparseConv46_1024-2048-(1, 1)': [2, 16], 'SparseConv47_2048-512-(1, 1)': [4, 16], 'SparseConv48_512-512-(3, 3)': [2, 16], 'SparseConv49_512-2048-(1, 1)': [4, 16], 'SparseConv50_2048-512-(1, 1)': [4, 16], 'SparseConv51_512-512-(3, 3)': [2, 16], 'SparseConv52_512-2048-(1, 1)': [4, 16], 'Linear0_2048-1000': [4, 16]}

Train:

After getting the layer-wise sparse schemes, we need to fine-tune with the schemes to recover the accuracy. The training code is based on NM-sparsity, where we made some changes to support flexible N:M schemes.

Below is an example of training layer-wise sparse resnet50 with 80% overall sparsity.

cd DominoSearch\DominoSearch\train\classification_sparsity_level\train_imagenet
 python -m torch.distributed.launch --nproc_per_node=8 ../train_imagenet.py --config ./configs/config_resnet50.yaml  --base_lr 0.01 --decay 0.0005 --epochs 120 --schemes_file ./schemes/resnet50_M16_0.80.txt --model_dir ./resnet50/resnet50_0.80_M16

Experiments

We provide the trained models of the experiments. Please check our paper for details and intepretations of the experiments.

ResNet50 experiments in section 4.1

Model Name TOP1 Accuracy Trained Model Searched schemes
resnet50 - 0.80 model size 76.7 google drive google drive
resnet50 - 0.875 model size 75.7 google drive google drive
resnet50 - 0.9375 model size 73.5 google drive google drive
resnet50 - 8x FLOPs 75.4 google drive google drive
resnet50- 16x FLOPs 73.4 google drive google drive

Ablation experiments of ResNet50 in section 5.3

Model Name TOP1 Accuracy Trained Model Train log
Ablation E3 76.1 google drive google drive
Ablation E4 76.4 google drive google drive
Ablation E6 76.6 google drive google drive
Ablation E7 75.6 google drive google drive

Citation

@inproceedings{
sun2021dominosearch,
title={DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks},
author={Wei Sun and Aojun Zhou and Sander Stuijk and Rob G. J. Wijnhoven and Andrew Nelson and Hongsheng Li and Henk Corporaal},
booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},
year={2021},
url={https://openreview.net/forum?id=IGrC6koW_g}
}
Image Segmentation Evaluation

Image Segmentation Evaluation Martin Keršner, [email protected] Evaluation

Martin Kersner 273 Oct 28, 2022
Unofficial Implement PU-Transformer

PU-Transformer-pytorch Pytorch unofficial implementation of PU-Transformer (PU-Transformer: Point Cloud Upsampling Transformer) https://arxiv.org/abs/

Lee Hyung Jun 7 Sep 21, 2022
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics

Dataset Cartography Code for the paper Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics at EMNLP 2020. This repository cont

AI2 125 Dec 22, 2022
OREO: Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning (NeurIPS 2021)

OREO: Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning (NeurIPS 2021) Video demo We here provide a video demo from co

20 Nov 25, 2022
Evaluating saliency methods on artificial data with different background types

Evaluating saliency methods on artificial data with different background types This repository contains the relevant code for the MedNeurips 2021 subm

2 Jul 05, 2022
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy" (ICLR 2022 Spotlight)

About Code release for Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy (ICLR 2022 Spotlight)

THUML @ Tsinghua University 221 Dec 31, 2022
The Codebase for Causal Distillation for Language Models.

Causal Distillation for Language Models Zhengxuan Wu*,Atticus Geiger*, Josh Rozner, Elisa Kreiss, Hanson Lu, Thomas Icard, Christopher Potts, Noah D.

Zen 20 Dec 31, 2022
HDMapNet: A Local Semantic Map Learning and Evaluation Framework

HDMapNet_devkit Devkit for HDMapNet. HDMapNet: A Local Semantic Map Learning and Evaluation Framework Qi Li, Yue Wang, Yilun Wang, Hang Zhao [Paper] [

Tsinghua MARS Lab 421 Jan 04, 2023
Re-implementation of the vector capsule with dynamic routing

VectorCapsule Re-implementation of the vector capsule with dynamic routing We implement the vector capsule and dynamic routing via graph neural networ

ZhenchaoTang 10 Feb 10, 2022
curl-impersonate: A special compilation of curl that makes it impersonate Chrome & Firefox

curl-impersonate A special compilation of curl that makes it impersonate real browsers. It can impersonate the four major browsers: Chrome, Edge, Safa

lwthiker 1.9k Jan 03, 2023
[ICCV'2021] Image Inpainting via Conditional Texture and Structure Dual Generation

[ICCV'2021] Image Inpainting via Conditional Texture and Structure Dual Generation

Xiefan Guo 122 Dec 11, 2022
Instance-level Image Retrieval using Reranking Transformers

Instance-level Image Retrieval using Reranking Transformers Fuwen Tan, Jiangbo Yuan, Vicente Ordonez, ICCV 2021. Abstract Instance-level image retriev

UVA Computer Vision 87 Jan 03, 2023
3rd Place Solution of the Traffic4Cast Core Challenge @ NeurIPS 2021

3rd Place Solution of Traffic4Cast 2021 Core Challenge This is the code for our solution to the NeurIPS 2021 Traffic4Cast Core Challenge. Paper Our so

7 Jul 25, 2022
Grammar Induction using a Template Tree Approach

Gitta Gitta ("Grammar Induction using a Template Tree Approach") is a method for inducing context-free grammars. It performs particularly well on data

Thomas Winters 36 Nov 15, 2022
DIT is a DTLS MitM proxy implemented in Python 3. It can intercept, manipulate and suppress datagrams between two DTLS endpoints and supports psk-based and certificate-based authentication schemes (RSA + ECC).

DIT - DTLS Interception Tool DIT is a MitM proxy tool to intercept DTLS traffic. It can intercept, manipulate and/or suppress DTLS datagrams between t

52 Nov 30, 2022
This repository contains the database and code used in the paper Embedding Arithmetic for Text-driven Image Transformation

This repository contains the database and code used in the paper Embedding Arithmetic for Text-driven Image Transformation (Guillaume Couairon, Holger

Meta Research 31 Oct 17, 2022
Rohit Ingole 2 Mar 24, 2022
Exploit ILP to learn symmetry breaking constraints of ASP programs.

ILP Symmetry Breaking Overview This project aims to exploit inductive logic programming to lift symmetry breaking constraints of ASP programs. Given a

Research Group Production Systems 1 Apr 13, 2022
[ICCV'21] Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment

CKDN The official implementation of the ICCV2021 paper "Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment" O

Multimedia Research 50 Dec 13, 2022
Playable Video Generation

Playable Video Generation Playable Video Generation Willi Menapace, Stéphane Lathuilière, Sergey Tulyakov, Aliaksandr Siarohin, Elisa Ricci Paper: ArX

Willi Menapace 136 Dec 31, 2022