Tree-based Search Graph for Approximate Nearest Neighbor Search

Related tags

Deep LearningTBSG
Overview

TBSG: Tree-based Search Graph for Approximate Nearest Neighbor Search.

TBSG is a graph-based algorithm for ANNS based on Cover Tree, which is also an approximation of Monotonic Search Network (MSNET). TBSG is very efficient with high precision.

Benchmark datasets

Datasets | No. of base | dimension | No. of query | download link
Sift | 1,000,000 | 128 | 10,000 | (http://corpus-texmex.irisa.fr/)
Gist | 1,000,000 | 300 | 1,000 | (http://corpus-texmex.irisa.fr/)
Glove | 1,183,514 | 100 | 10,000 | (http://downloads.zjulearning.org.cn/data/glove-100.tar.gz)
Crawl | 1,989,995 | 300 | 10,000 | (http://commoncrawl.org/)

How to use TBSG

1) compile

  • Prerequisite : openmp, cmake, eigen3
$ cd /path/to/project  
$ cmake . && make  

2) build an approximate kNNG

We use efanna_graph to build the kNNG.

3) create a TBSG index

$ cd /path/to/project/  
$ ./TBSG_index data_path M S MP nnfile save_path  

data_path is the path of base data.
M is the maximum of size of neighbors.
S is the candidate set size to build TBSG.
MP is the minimum of min_prob.
nnfile is the file of k nearest neighbor graph.
save_path is the path to save the index.

4) search with TBSG index

$ cd /path/to/project/
$ ./TBSG_search data_path query_path groundtruth_path save_path step

data_path is the path of base data.
query_path is the path of query data.
groundtruth is the path of groundtruth data.
save_path is the path to save the index.
step is the step size to expand the search pool.

Parameters used for four datasets

parameters for building kNNG

Dataset K L iter S R
Sift 200 200 12 10 100
Gist 400 400 12 15 100
Glove 400 420 12 20 300
Crawl 400 420 12 20 100

parameters for building index

Datasets M S MP
Sift 50 100 0.53
Gist 70 200 0.515
Glove 80 300 0.53
Crawl 50 200 0.53
Owner
Fanxbin
Fanxbin
Animal Sound Classification (Cats Vrs Dogs Audio Sentiment Classification)

this is a simple artificial neural network model using deep learning and torch-audio to classify cats and dog sounds.

crispengari 3 Dec 05, 2022
SFD implement with pytorch

S³FD: Single Shot Scale-invariant Face Detector A PyTorch Implementation of Single Shot Scale-invariant Face Detector Description Meanwhile train hand

Jun Li 251 Dec 22, 2022
List of papers, code and experiments using deep learning for time series forecasting

Deep Learning Time Series Forecasting List of state of the art papers focus on deep learning and resources, code and experiments using deep learning f

Alexander Robles 2k Jan 06, 2023
Establishing Strong Baselines for TripClick Health Retrieval; ECIR 2022

TripClick Baselines with Improved Training Data Welcome 🙌 to the hub-repo of our paper: Establishing Strong Baselines for TripClick Health Retrieval

Sebastian Hofstätter 3 Nov 03, 2022
💃 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena

💃 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena.

Heidelberg-NLP 17 Nov 07, 2022
Differentiable Quantum Chemistry (only Differentiable Density Functional Theory and Hartree Fock at the moment)

DQC: Differentiable Quantum Chemistry Differentiable quantum chemistry package. Currently only support differentiable density functional theory (DFT)

75 Dec 02, 2022
Code for reproducing experiments in "Improved Training of Wasserstein GANs"

Improved Training of Wasserstein GANs Code for reproducing experiments in "Improved Training of Wasserstein GANs". Prerequisites Python, NumPy, Tensor

Ishaan Gulrajani 2.2k Jan 01, 2023
Pytorch-Swin-Unet-V2 - a modified version of Swin Unet based on Swin Transfomer V2

Swin Unet V2 Swin Unet V2 is a modified version of Swin Unet arxiv based on Swin

Chenxu Peng 26 Dec 03, 2022
PoseCamera is python based SDK for human pose estimation through RGB webcam.

PoseCamera PoseCamera is python based SDK for human pose estimation through RGB webcam. Install install posecamera package through pip pip install pos

WonderTree 7 Jul 20, 2021
Medical Image Segmentation using Squeeze-and-Expansion Transformers

Medical Image Segmentation using Squeeze-and-Expansion Transformers Introduction This repository contains the code of the IJCAI'2021 paper 'Medical Im

askerlee 172 Dec 20, 2022
This repository contains the source code of an efficient 1D probabilistic model for music time analysis proposed in ICASSP2022 venue.

Jump Reward Inference for 1D Music Rhythmic State Spaces An implementation of the probablistic jump reward inference model for music rhythmic informat

Mojtaba Heydari 25 Dec 16, 2022
Constraint-based geometry sketcher for blender

Constraint-based sketcher addon for Blender that allows to create precise 2d shapes by defining a set of geometric constraints like tangent, distance,

1.7k Dec 31, 2022
Implementation of TabTransformer, attention network for tabular data, in Pytorch

Tab Transformer Implementation of Tab Transformer, attention network for tabular data, in Pytorch. This simple architecture came within a hair's bread

Phil Wang 420 Jan 05, 2023
PyTorch implementation of Deformable Convolution

PyTorch implementation of Deformable Convolution !!!Warning: There is some issues in this implementation and this repo is not maintained any more, ple

Wei Ouyang 893 Dec 18, 2022
"Projelerle Yapay Zeka Ve Bilgisayarlı Görü" Kitabımın projeleri

"Projelerle Yapay Zeka Ve Bilgisayarlı Görü" Kitabımın projeleri Bu Github Reposundaki tüm projeler; kaleme almış olduğum "Projelerle Yapay Zekâ ve Bi

Ümit Aksoylu 4 Aug 03, 2022
Canonical Appearance Transformations

CAT-Net: Learning Canonical Appearance Transformations Code to accompany our paper "How to Train a CAT: Learning Canonical Appearance Transformations

STARS Laboratory 54 Dec 24, 2022
Code for EMNLP2021 paper "Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training"

VoCapXLM Code for EMNLP2021 paper Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training Environment DockerFile: dancingso

Bo Zheng 15 Jul 28, 2022
Automatic differentiation with weighted finite-state transducers.

GTN: Automatic Differentiation with WFSTs Quickstart | Installation | Documentation What is GTN? GTN is a framework for automatic differentiation with

100 Dec 29, 2022
Neural implicit reconstruction experiments for the Vector Neuron paper

Neural Implicit Reconstruction with Vector Neurons This repository contains code for the neural implicit reconstruction experiments in the paper Vecto

Congyue Deng 35 Jan 02, 2023
A PyTorch implementation of the Relational Graph Convolutional Network (RGCN).

Torch-RGCN Torch-RGCN is a PyTorch implementation of the RGCN, originally proposed by Schlichtkrull et al. in Modeling Relational Data with Graph Conv

Thiviyan Singam 66 Nov 30, 2022