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

Last update: Sep 10, 2022

Related tags

Deep Learning DominoSearch

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}
}

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

Related tags

Overview

DominoSearch

Search:

Train:

Experiments

ResNet50 experiments in section 4.1

Ablation experiments of ResNet50 in section 5.3

Citation

Owner

SatelliteSfM - A library for solving the satellite structure from motion problem

This package implements THOR: Transformer with Stochastic Experts.

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation (ICCV 2021)

Official Pytorch Code for the paper TransWeather

Official implementation of particle-based models (GNS and DPI-Net) on the Physion dataset.

source code for https://arxiv.org/abs/2005.11248 "Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics"

TensorFlow Tutorials with YouTube Videos

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

This is 2nd term discrete maths project done by UCU students that uses backtracking to solve various problems.

Keqing Chatbot With Python

Spam your friends and famly and when you do your famly will disown you and you will have no friends.

Pytorch Implementation of Various Point Transformers

Code for ICCV 2021 paper Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes using Scene Graphs

Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.

The CLRS Algorithmic Reasoning Benchmark

Spatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021

The implementation of "Optimizing Shoulder to Shoulder: A Coordinated Sub-Band Fusion Model for Real-Time Full-Band Speech Enhancement"

Official repository of the AAAI'2022 paper "Contrast and Generation Make BART a Good Dialogue Emotion Recognizer"

Simulator for FRC 2022 challenge: Rapid React