GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → iCVTEAM → TDRG

iCVTEAM / TDRG

Licence: Apache-2.0 license
Transformer-based Dual Relation Graph for Multi-label Image Recognition. ICCV 2021

Programming Languages

python
139335 projects - #7 most used programming language

Labels

transformergcnmulti-label-image-classification

Projects that are alternatives of or similar to TDRG

PDN
The official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
Stars: ✭ 44 (+37.5%)
Mutual labels:  transformer, gcn
KitanaQA
KitanaQA: Adversarial training and data augmentation for neural question-answering models
Stars: ✭ 58 (+81.25%)
Mutual labels:  transformer
proc-that
proc(ess)-that - easy extendable ETL tool for Node.js. Written in TypeScript.
Stars: ✭ 25 (-21.87%)
Mutual labels:  transformer
DolboNet
Русскоязычный чат-бот для Discord на архитектуре Transformer
Stars: ✭ 53 (+65.63%)
Mutual labels:  transformer
basis-expansions
Basis expansion transformers in sklearn style.
Stars: ✭ 74 (+131.25%)
Mutual labels:  transformer
german-sentiment
A data set and model for german sentiment classification.
Stars: ✭ 37 (+15.63%)
Mutual labels:  transformer
ASAP
AAAI 2020 - ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations
Stars: ✭ 83 (+159.38%)
Mutual labels:  gcn
learningspoons
nlp lecture-notes and source code
Stars: ✭ 29 (-9.37%)
Mutual labels:  transformer
BGCN
A Tensorflow implementation of "Bayesian Graph Convolutional Neural Networks" (AAAI 2019).
Stars: ✭ 129 (+303.13%)
Mutual labels:  gcn
FasterTransformer
Transformer related optimization, including BERT, GPT
Stars: ✭ 1,571 (+4809.38%)
Mutual labels:  transformer
GaitGraph
Official repository for "GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition" (ICIP'21)
Stars: ✭ 68 (+112.5%)
Mutual labels:  gcn
TRAR-VQA
[ICCV 2021] TRAR: Routing the Attention Spans in Transformers for Visual Question Answering -- Official Implementation
Stars: ✭ 49 (+53.13%)
Mutual labels:  transformer
tensorflow-ml-nlp-tf2
텐서플로2와 머신러닝으로 시작하는 자연어처리 (로지스틱회귀부터 BERT와 GPT3까지) 실습자료
Stars: ✭ 245 (+665.63%)
Mutual labels:  transformer
Zero-Shot-TTS
Unofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Stars: ✭ 33 (+3.13%)
Mutual labels:  transformer
GNN-Recommender-Systems
An index of recommendation algorithms that are based on Graph Neural Networks.
Stars: ✭ 505 (+1478.13%)
Mutual labels:  gcn
Neural-Machine-Translation
Several basic neural machine translation models implemented by PyTorch & TensorFlow
Stars: ✭ 29 (-9.37%)
Mutual labels:  transformer
Highway-Transformer
[ACL‘20] Highway Transformer: A Gated Transformer.
Stars: ✭ 26 (-18.75%)
Mutual labels:  transformer
php-json-api
JSON API transformer outputting valid (PSR-7) API Responses.
Stars: ✭ 68 (+112.5%)
Mutual labels:  transformer
sticker2
Further developed as SyntaxDot: https://github.com/tensordot/syntaxdot
Stars: ✭ 14 (-56.25%)
Mutual labels:  transformer
Graphormer
Graphormer is a deep learning package that allows researchers and developers to train custom models for molecule modeling tasks. It aims to accelerate the research and application in AI for molecule science, such as material design, drug discovery, etc.
Stars: ✭ 1,194 (+3631.25%)
Mutual labels:  transformer
View All Similar Projects ➔

TDRG

Pytorch implementation of Transformer-based Dual Relation Graph for Multi-label Image Recognition. ICCV 2021

TDRG

Prerequisites

Python 3.6+

Pytorch 1.6

CUDA 10.1

Tesla V100 × 2

Datasets

Model

  • MS-COCO: the name of parameters in our original network is different from the public one, hence if you want to test the performance of TDRG on MS-COCO, please download the checkpoint into checkpoint/COCO2014 folder and replace the function load_checkpoint with load_origin_checkpoint in trainer.py.

Train

CUDA_VISIBLE_DEVICES=0,1 python main.py  --data COCO2014 --data_root_dir $DATA_PATH$ --save_dir $SAVE_PATH$ --i 448  --lr 0.03 -b 64

Test

python main.py  --data COCO2014 --data_root_dir $DATA_PATH$ --save_dir $SAVE_PATH$ --i 448  --lr 0.03 -b 64 -e --resume checkpoint/COCO2014/checkpoint_COCO.pth

Visualization

vis

Citation

  • If you find this work is helpful, please cite our paper
@InProceedings{Zhao2021TDRG,
    author    = {Zhao, Jiawei and Yan, Ke and Zhao, Yifan and Guo, Xiaowei and Huang, Feiyue and Li, Jia},
    title     = {Transformer-Based Dual Relation Graph for Multi-Label Image Recognition},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {163-172}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].