Implementation of Deformable Attention in Pytorch from the paper "Vision Transformer with Deformable Attention"

Related tags

Deep Learningdeep-learningartificial-intelligenceattention-mechanism
Overview

Deformable Attention

Implementation of Deformable Attention from this paper in Pytorch, which appears to be an improvement to what was proposed in DETR. The relative positional embedding has also been modified for better extrapolation, using the Continuous Positional Embedding proposed in SwinV2.

Install

$ pip install deformable-attention

Usage

import torch
from deformable_attention import DeformableAttention

attn = DeformableAttention(
    dim = 512,                   # feature dimensions
    dim_head = 64,               # dimension per head
    heads = 8,                   # attention heads
    dropout = 0.,                # dropout
    downsample_factor = 4,       # downsample factor (r in paper)
    offset_scale = 4,            # scale of offset, maximum offset
    offset_groups = None,        # number of offset groups, should be multiple of heads
    offset_kernel_size = 6,      # offset kernel size
)

x = torch.randn(1, 512, 64, 64)
attn(x) # (1, 512, 64, 64)

3d deformable attention

import torch
from deformable_attention import DeformableAttention3D

attn = DeformableAttention3D(
    dim = 512,                          # feature dimensions
    dim_head = 64,                      # dimension per head
    heads = 8,                          # attention heads
    dropout = 0.,                       # dropout
    downsample_factor = (2, 8, 8),      # downsample factor (r in paper)
    offset_scale = (2, 8, 8),           # scale of offset, maximum offset
    offset_kernel_size = (4, 10, 10),   # offset kernel size
)

x = torch.randn(1, 512, 10, 32, 32) # (batch, dimension, frames, height, width)
attn(x) # (1, 512, 10, 32, 32)

1d deformable attention for good measure

import torch
from deformable_attention import DeformableAttention1D

attn = DeformableAttention1D(
    dim = 128,
    downsample_factor = 4,
    offset_scale = 2,
    offset_kernel_size = 6
)

x = torch.randn(1, 128, 512)
attn(x) # (1, 128, 512)

Citation

@misc{xia2022vision,
    title   = {Vision Transformer with Deformable Attention}, 
    author  = {Zhuofan Xia and Xuran Pan and Shiji Song and Li Erran Li and Gao Huang},
    year    = {2022},
    eprint  = {2201.00520},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}
@misc{liu2021swin,
    title   = {Swin Transformer V2: Scaling Up Capacity and Resolution},
    author  = {Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
    year    = {2021},
    eprint  = {2111.09883},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}
You might also like...
Some code of the implements of Geological Modeling Using 3D Pixel-Adaptive and Deformable Convolutional Neural Network

3D-GMPDCNN Geological Modeling Using 3D Pixel-Adaptive and Deformable Convolutional Neural Network PyTorch implementation of "Geological Modeling Usin

null 5 Nov 21, 2022
MoCoPnet - Deformable 3D Convolution for Video Super-Resolution
MoCoPnet - Deformable 3D Convolution for Video Super-Resolution

Deformable 3D Convolution for Video Super-Resolution Pytorch implementation of l

Xinyi Ying 28 Dec 15, 2022
3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021)

3DDUNET This is the code for 3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021) Conference Paper Link Dataset We use SMOID dataset

null 1 Jan 7, 2022
Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones
Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones

HaloNet - Pytorch Implementation of the Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones. This re

Phil Wang 189 Nov 22, 2022
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

Memory Efficient Attention Pytorch Implementation of a memory efficient multi-head attention as proposed in the paper, Self-attention Does Not Need O(

Phil Wang 180 Jan 5, 2023
Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch
Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch

Transformer in Transformer Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image c

Phil Wang 272 Dec 23, 2022
Official Pytorch Implementation of Relational Self-Attention: What's Missing in Attention for Video Understanding
Official Pytorch Implementation of Relational Self-Attention: What's Missing in Attention for Video Understanding

Relational Self-Attention: What's Missing in Attention for Video Understanding This repository is the official implementation of "Relational Self-Atte

mandos 43 Dec 7, 2022
The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

TimeSformer This is an official pytorch implementation of Is Space-Time Attention All You Need for Video Understanding?. In this repository, we provid

Facebook Research 1k Dec 31, 2022
An implementation demo of the ICLR 2021 paper Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks in PyTorch.

Neural Attention Distillation This is an implementation demo of the ICLR 2021 paper Neural Attention Distillation: Erasing Backdoor Triggers from Deep

Yige-Li 84 Jan 4, 2023
Comments
  • The relationship between 'dim' and 'inner_dim'

    The relationship between 'dim' and 'inner_dim'

    Hi, I have a question about DeformableAttention module,

    I calculated the output volumes of the forward processes step by step, According to my calculation, the code works only when 'dim' and 'inner_dim' is same.

    Is there any reason why you implement it this way?

    Best regards, Hankyu

    opened by hanq0212 4
  • TypeError: meshgrid() got an unexpected keyword argument 'indexing'

    TypeError: meshgrid() got an unexpected keyword argument 'indexing'

    @lucidrains while trying to perform import torch from deformable_attention import DeformableAttention

    attn = DeformableAttention( dim = 512, # feature dimensions dim_head = 64, # dimension per head heads = 8, # attention heads dropout = 0., # dropout downsample_factor = 4, # downsample factor (r in paper) offset_scale = 4, # scale of offset, maximum offset offset_groups = None, # number of offset groups, should be multiple of heads offset_kernel_size = 6, # offset kernel size )

    x = torch.randn(1, 512, 64, 64) attn(x)

    Got error below from the line.. Kindly help

    https://github.com/lucidrains/deformable-attention/blob/9f3c0ae35652ce54687e0db409921018bfca3310/deformable_attention/deformable_attention_2d.py#L26

    opened by ChidanandKumarKS 1
Owner
Phil Wang
Working with Attention. It's all we need
Phil Wang
GitHub Repository
This repository contains demos I made with the Transformers library by HuggingFace.

Transformers-Tutorials Hi there! This repository contains demos I made with the Transformers library by 🤗 HuggingFace. Currently, all of them are imp

3.5k Jan 01, 2023
Feature board for ERPNext

ERPNext Feature Board Feature board for ERPNext Development Prerequisites k3d kubectl helm bench Install K3d Cluster # export K3D_FIX_CGROUPV2=1 # use

Revant Nandgaonkar 16 Nov 09, 2022
Dynamical Wasserstein Barycenters for Time Series Modeling

Dynamical Wasserstein Barycenters for Time Series Modeling This is the code related for the Dynamical Wasserstein Barycenter model published in Neurip

8 Sep 09, 2022
A Sklearn-like Framework for Hyperparameter Tuning and AutoML in Deep Learning projects. Finally have the right abstractions and design patterns to properly do AutoML. Let your pipeline steps have hyperparameter spaces. Enable checkpoints to cut duplicate calculations. Go from research to production environment easily.

Neuraxle Pipelines Code Machine Learning Pipelines - The Right Way. Neuraxle is a Machine Learning (ML) library for building machine learning pipeline

Neuraxio 555 Dec 24, 2022
Code repo for "Transformer on a Diet" paper

Transformer on a Diet Reference: C Wang, Z Ye, A Zhang, Z Zhang, A Smola. "Transformer on a Diet". arXiv preprint arXiv (2020). Installation pip insta

cgraywang 31 Sep 26, 2021
MISSFormer: An Effective Medical Image Segmentation Transformer

MISSFormer Code for paper "MISSFormer: An Effective Medical Image Segmentation Transformer". Please read our preprint at the following link: paper_add

Fong 22 Dec 24, 2022
Official codebase for Pretrained Transformers as Universal Computation Engines.

universal-computation Overview Official codebase for Pretrained Transformers as Universal Computation Engines. Contains demo notebook and scripts to r

Kevin Lu 210 Dec 28, 2022
Sandbox for training deep learning networks

Deep learning networks This repo is used to research convolutional networks primarily for computer vision tasks. For this purpose, the repo contains (

Oleg Sémery 2.7k Jan 01, 2023
Soomvaar is the repo which 🏩 contains different collection of 👨‍💻🚀code in Python and 💫✨Machine 👬🏼 learning algorithms📗📕 that is made during 📃 my practice and learning of ML and Python✨💥

Soomvaar 📌 Introduction Soomvaar is the collection of various codes implement in machine learning and machine learning algorithms with python on coll

Felix-Ayush 42 Dec 30, 2022
A PyTorch implementation for our paper "Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation".

Dual-Contrastive-Learning A PyTorch implementation for our paper "Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation". Y

hoshi-hiyouga 85 Dec 26, 2022
Code for our ACL 2021 paper "One2Set: Generating Diverse Keyphrases as a Set"

One2Set This repository contains the code for our ACL 2021 paper “One2Set: Generating Diverse Keyphrases as a Set”. Our implementation is built on the

Jiacheng Ye 63 Jan 05, 2023
NumQMBasic - A mini-course offered to Undergrad physics students

The best way to use this material is by forking it by click the Fork button at the top, right corner. Then you will get your own copy to play with! Th

Raghu 35 Dec 05, 2022
TigerLily: Finding drug interactions in silico with the Graph.

Drug Interaction Prediction with Tigerlily Documentation | Example Notebook | Youtube Video | Project Report Tigerlily is a TigerGraph based system de

Benedek Rozemberczki 91 Dec 30, 2022
McGill Physics Hackathon 2021: Reaction-Diffusion Models for the Generation of Biological Patterns

DiffuseAnimals: Reaction-Diffusion Models for the Generation of Biological Patterns Introduction Reaction-diffusion equations can be utilized in order

Austin Szuminsky 2 Mar 07, 2022
Hyperbolic Hierarchical Clustering.

Hyperbolic Hierarchical Clustering (HypHC) This code is the official PyTorch implementation of the NeurIPS 2020 paper: From Trees to Continuous Embedd

HazyResearch 154 Dec 15, 2022
Neural networks applied in recognizing guitar chords using python, AutoML.NET with C# and .NET Core

Chord Recognition Demo application The demo application is written in C# with .NETCore. As of July 9, 2020, the only version available is for windows

Andres Mauricio Rondon Patiño 24 Oct 22, 2022
Neural Koopman Lyapunov Control

Neural-Koopman-Lyapunov-Control Code for our paper: Neural Koopman Lyapunov Control Requirements dReal4: v4.19.02.1 PyTorch: 1.2.0 The learning framew

Vrushabh Zinage 6 Dec 24, 2022
Collection of sports betting AI tools.

sports-betting sports-betting is a collection of tools that makes it easy to create machine learning models for sports betting and evaluate their perf

George Douzas 109 Dec 31, 2022
natural image generation using ConvNets

The Eyescream Project Generating Natural Images using Neural Networks. For our research summary on this work, please read the Arxiv paper: http://arxi

Meta Archive 601 Nov 23, 2022
Built a deep neural network (DNN) that functions as an end-to-end machine translation pipeline

Built a deep neural network (DNN) that functions as an end-to-end machine translation pipeline. The pipeline accepts english text as input and returns the French translation.

Afropunk Technologist 1 Jan 24, 2022