Official code for paper "Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight"

Related tags

Deep LearningDemystifyLocalViT
Overview

Demysitifing Local Vision Transformer, arxiv

This is the official PyTorch implementation of our paper. We simply replace local self attention by (dynamic) depth-wise convolution with lower computational cost. The performance is on par with the Swin Transformer.

Besides, the main contribution of our paper is the theorical and detailed comparison between depth-wise convolution and local self attention from three aspects: sparse connectivity, weight sharing and dynamic weight. By this paper, we want community to rethinking the local self attention and depth-wise convolution, and the basic model architeture designing rules.

Codes and models for object detection and semantic segmentation are avaliable in Detection and Segmentation.

We also give MLP based Swin Transformer models and Inhomogenous dynamic convolution in the ablation studies. These codes and models will coming soon.

Reference

@article{han2021demystifying,
  title={Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight},
  author={Han, Qi and Fan, Zejia and Dai, Qi and Sun, Lei and Cheng, Ming-Ming and Liu, Jiaying and Wang, Jingdong},
  journal={arXiv preprint arXiv:2106.04263},
  year={2021}
}

1. Requirements

torch>=1.5.0, torchvision, timm, pyyaml; apex-amp

data perpare: ImageNet dataset with the following structure:

│imagenet/
├──train/
│  ├── n01440764
│  │   ├── n01440764_10026.JPEG
│  │   ├── n01440764_10027.JPEG
│  │   ├── ......
│  ├── ......
├──val/
│  ├── n01440764
│  │   ├── ILSVRC2012_val_00000293.JPEG
│  │   ├── ILSVRC2012_val_00002138.JPEG
│  │   ├── ......
│  ├── ......

2. Trainning

For tiny model, we train with batch-size 128 on 8 GPUs. When trainning base model, we use batch-size 64 on 16 GPUs with OpenMPI to keep the total batch-size unchanged. (With the same trainning setting, the base model couldn't train with AMP due to the anomalous gradient values.)

Please change the data path in sh scripts first.

For tiny model:

bash scripts/run_dwnet_tiny_patch4_window7_224.sh 
bash scripts/run_dynamic_dwnet_tiny_patch4_window7_224.sh

For base model, use multi node with OpenMPI:

bash scripts/run_dwnet_base_patch4_window7_224.sh 
bash scripts/run_dynamic_dwnet_base_patch4_window7_224.sh

3. Evaluation

python -m torch.distributed.launch --nproc_per_node 1 --master_port 12345 main.py --cfg configs/change_to_config_file --resume /path/to/model --data-path /path/to/imagenet --eval

4. Models

Models are provided by training on ImageNet with resolution 224.

Model #params FLOPs Top1 Acc Download
dwnet_tiny 24M 3.8G 81.2 github
dynamic_dwnet_tiny 51M 3.8G 81.8 github
dwnet_base 74M 12.9G 83.2 github
dynamic_dwnet_base 162M 13.0G 83.2 github

Detection (see Detection for details):

Backbone Pretrain Lr Schd box mAP mask mAP #params FLOPs config model
DWNet-T ImageNet-1K 3x 49.9 43.4 82M 730G config github
DWNet-B ImageNet-1K 3x 51.0 44.1 132M 924G config github
Dynamic-DWNet-T ImageNet-1K 3x 50.5 43.7 108M 730G config github
Dynamic-DWNet-B ImageNet-1K 3x 51.2 44.4 219M 924G config github

Segmentation (see Segmentation for details):

Backbone Pretrain Lr Schd mIoU #params FLOPs config model
DWNet-T ImageNet-1K 160K 45.5 56M 928G config github
DWNet-B ImageNet-1K 160K 48.3 108M 1129G config github
Dynamic-DWNet-T ImageNet-1K 160K 45.7 83M 928G config github
Dynamic-DWNet-B ImageNet-1K 160K 48.0 195M 1129G config github

LICENSE

This repo is under the MIT license. Some codes are borrow from Swin Transformer.

You might also like...
Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.

Learning Associative Inference Using Fast Weight Memory This repository contains the offical code for the paper Learning Associative Inference Using F

Imanol Schlag 18 Oct 12, 2022
Official PyTorch code for CVPR 2020 paper
Official PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"

Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision https://arxiv.org/abs/2003.00393 Abstract Active learning (AL) aims to min

Denis 29 Nov 21, 2022
Official Code for ICML 2021 paper
Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline Ankit Goyal, Hei Law, Bowei Liu, Alejandro Newell, Jia Deng Internati

Princeton Vision & Learning Lab 115 Jan 4, 2023
CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.
CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.

selfcontact This repo is part of our project: On Self-Contact and Human Pose. [Project Page] [Paper] [MPI Project Page] It includes the main function

Lea Müller 68 Dec 6, 2022
CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.
CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.

SMPLify-XMC This repo is part of our project: On Self-Contact and Human Pose. [Project Page] [Paper] [MPI Project Page] License Software Copyright Lic

Lea Müller 83 Dec 14, 2022
Official code of paper "PGT: A Progressive Method for Training Models on Long Videos" on CVPR2021

PGT Code for paper PGT: A Progressive Method for Training Models on Long Videos. Install Run pip install -r requirements.txt. Run python setup.py buil

Bo Pang 27 Mar 30, 2022
This is the official code of our paper
This is the official code of our paper "Diversity-based Trajectory and Goal Selection with Hindsight Experience Relay" (PRICAI 2021)

Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay This is the official implementation of our paper "Diversity-based Traje

Tianhong Dai 6 Jul 18, 2022
The official code for paper "R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling".

R2D2 This is the official code for paper titled "R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Mode

Alipay 49 Dec 17, 2022
Official repository with code and data accompanying the NAACL 2021 paper "Hurdles to Progress in Long-form Question Answering" (https://arxiv.org/abs/2103.06332).

Hurdles to Progress in Long-form Question Answering This repository contains the official scripts and datasets accompanying our NAACL 2021 paper, "Hur

Kalpesh Krishna 41 Nov 8, 2022
Comments
  • CVE-2007-4559 Patch

    CVE-2007-4559 Patch

    Patching CVE-2007-4559

    Hi, we are security researchers from the Advanced Research Center at Trellix. We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a 15 year old bug in the Python tarfile package. By using extract() or extractall() on a tarfile object without sanitizing input, a maliciously crafted .tar file could perform a directory path traversal attack. We found at least one unsantized extractall() in your codebase and are providing a patch for you via pull request. The patch essentially checks to see if all tarfile members will be extracted safely and throws an exception otherwise. We encourage you to use this patch or your own solution to secure against CVE-2007-4559. Further technical information about the vulnerability can be found in this blog.

    If you have further questions you may contact us through this projects lead researcher Kasimir Schulz.

    opened by TrellixVulnTeam 0
  • Possible bug?

    Possible bug? 

    class DynamicDWConv(nn.Module):
    def __init__(self, dim, kernel_size, bias=True, stride=1, padding=1, groups=1, reduction=4):
        super().__init__()
        self.dim = dim
        self.kernel_size = kernel_size
        self.stride = stride 
        self.padding = padding 
        self.groups = groups 

        self.pool = nn.AdaptiveAvgPool2d((1, 1))
        self.conv1 = nn.Conv2d(dim, dim // reduction, 1, bias=False)
        self.bn = nn.BatchNorm2d(dim // reduction)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(dim // reduction, dim * kernel_size * kernel_size, 1)
        if bias:
            self.bias = nn.Parameter(torch.zeros(dim))
        else:
            self.bias = None

    def forward(self, x):
        b, c, h, w = x.shape
        weight = self.conv2(self.relu(self.bn(self.conv1(self.pool(x)))))
        weight = weight.view(b * self.dim, 1, self.kernel_size, self.kernel_size)
        x = F.conv2d(x.reshape(1, -1, h, w), weight, self.bias.repeat(b), stride=self.stride, padding=self.padding, groups=b * self.groups)
        x = x.view(b, c, x.shape[-2], x.shape[-1])
        return x

    This function seems to give error when groups is not equal to dim.

    opened by yxchng 0
Owner
Attention for Vision and Visualization
GitHub Repository
Sinkformers: Transformers with Doubly Stochastic Attention

Code for the paper : "Sinkformers: Transformers with Doubly Stochastic Attention" Paper You will find our paper here. Compat This package has been dev

Michael E. Sander 31 Dec 29, 2022
The repo of Feedback Networks, CVPR17

Feedback Networks http://feedbacknet.stanford.edu/ Paper: Feedback Networks, CVPR 2017. Amir R. Zamir*,Te-Lin Wu*, Lin Sun, William B. Shen, Bertram E

Stanford Vision and Learning Lab 87 Nov 19, 2022
Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy.

Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy. Now with tensorflow 1.0 support. Evaluation usa

Marcel R. 349 Aug 06, 2022
MonoRCNN is a monocular 3D object detection method for automonous driving

MonoRCNN MonoRCNN is a monocular 3D object detection method for automonous driving, published at ICCV 2021. This project is an implementation of MonoR

87 Dec 27, 2022
A collection of Google research projects related to Federated Learning and Federated Analytics.

Federated Research Federated Research is a collection of research projects related to Federated Learning and Federated Analytics. Federated learning i

Google Research 483 Jan 05, 2023
PyTorch implementation of ARM-Net: Adaptive Relation Modeling Network for Structured Data.

A ready-to-use framework of latest models for structured (tabular) data learning with PyTorch. Applications include recommendation, CRT prediction, healthcare analytics, and etc.

48 Nov 30, 2022
Learning hierarchical attention for weakly-supervised chest X-ray abnormality localization and diagnosis

Hierarchical Attention Mining (HAM) for weakly-supervised abnormality localization This is the official PyTorch implementation for the HAM method. Pap

Xi Ouyang 22 Jan 02, 2023
Official PaddlePaddle implementation of Paint Transformer

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction [Paper] [Paddle Implementation] Update We have optimized the serial inference p

TianweiLin 284 Dec 31, 2022
Nest Protect integration for Home Assistant. This will allow you to integrate your smoke, heat, co and occupancy status real-time in HA.

Nest Protect integration for Home Assistant Custom component for Home Assistant to interact with Nest Protect devices via an undocumented and unoffici

Mick Vleeshouwer 175 Dec 29, 2022
PyTorch implementation of deep GRAph Contrastive rEpresentation learning (GRACE).

GRACE The official PyTorch implementation of deep GRAph Contrastive rEpresentation learning (GRACE). For a thorough resource collection of self-superv

Big Data and Multi-modal Computing Group, CRIPAC 186 Dec 27, 2022
AWS documentation corpus for zero-shot open-book question answering.

aws-documentation We present the AWS documentation corpus, an open-book QA dataset, which contains 25,175 documents along with 100 matched questions a

Sia Gholami 2 Jul 07, 2022
An experiment to bait a generalized frontrunning MEV bot

Honeypot 🍯 A simple experiment that: Creates a honeypot contract Baits a generalized fronturnning bot with a unique transaction Analyze bot behaviour

0x1355 14 Nov 24, 2022
Gym-TORCS is the reinforcement learning (RL) environment in TORCS domain with OpenAI-gym-like interface.

Gym-TORCS Gym-TORCS is the reinforcement learning (RL) environment in TORCS domain with OpenAI-gym-like interface. TORCS is the open-rource realistic

naoto yoshida 400 Dec 27, 2022
MODNet: Trimap-Free Portrait Matting in Real Time

MODNet is a model for real-time portrait matting with only RGB image input.

Zhanghan Ke 2.8k Dec 30, 2022
PyTorch implementation of EGVSR: Efficcient & Generic Video Super-Resolution (VSR)

This is a PyTorch implementation of EGVSR: Efficcient & Generic Video Super-Resolution (VSR), using subpixel convolution to optimize the inference speed of TecoGAN VSR model. Please refer to the offi

789 Jan 04, 2023
Adaptive Dropblock Enhanced GenerativeAdversarial Networks for Hyperspectral Image Classification

This repo holds the codes of our paper: Adaptive Dropblock Enhanced GenerativeAdversarial Networks for Hyperspectral Image Classification, which is ac

Feng Gao 17 Dec 28, 2022
A simple configurable bot for sending arXiv article alert by mail

arXiv-newsletter A simple configurable bot for sending arXiv article alert by mail. Prerequisites PyYAML=5.3.1 arxiv=1.4.0 Configuration All config

SXKDZ 21 Nov 09, 2022
LaneDetectionAndLaneKeeping - Lane Detection And Lane Keeping

LaneDetectionAndLaneKeeping This project is part of my bachelor's thesis. The go

5 Jun 27, 2022
Pytorch implementation of the paper "COAD: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking."

Expert-Linking Pytorch implementation of the paper "COAD: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking." This is

BoChen 12 Jan 01, 2023
Graph neural network message passing reframed as a Transformer with local attention

Adjacent Attention Network An implementation of a simple transformer that is equivalent to graph neural network where the message passing is done with

Phil Wang 49 Dec 28, 2022