TransReID: Transformer-based Object Re-Identification

Last update: Dec 30, 2022

Related tags

Overview

TransReID: Transformer-based Object Re-Identification [arxiv]

The official repository for TransReID: Transformer-based Object Re-Identification achieves state-of-the-art performances on object re-ID, including person re-ID and vehicle re-ID.

Pipeline

Abaltion Study of Transformer-based Strong Baseline

Requirements

Installation

pip install -r requirements.txt
(we use /torch 1.6.0 /torchvision 0.7.0 /timm 0.3.2 /cuda 10.1 / 16G or 32G V100 for training and evaluation.
Note that we use torch.cuda.amp to accelerate speed of training which requires pytorch >=1.6)

Prepare Datasets

mkdir data

Download the person datasets Market-1501, MSMT17, DukeMTMC-reID,Occluded-Duke, and the vehicle datasets VehicleID, VeRi-776, Then unzip them and rename them under the directory like

data
├── market1501
│   └── images ..
├── MSMT17
│   └── images ..
├── dukemtmcreid
│   └── images ..
├── Occluded_Duke
│   └── images ..
├── VehicleID_V1.0
│   └── images ..
└── VeRi
    └── images ..

Prepare DeiT or ViT Pre-trained Models

You need to download the ImageNet pretrained transformer model : ViT-Base, ViT-Small, DeiT-Small, DeiT-Base

Training

We utilize 1 GPU for training.

python train.py --config_file configs/transformer_base.yml MODEL.DEVICE_ID "('your device id')" MODEL.STRIDE_SIZE ${1} MODEL.SIE_CAMERA ${2} MODEL.SIE_VIEW ${3} MODEL.JPM ${4} MODEL.TRANSFORMER_TYPE ${5} OUTPUT_DIR ${OUTPUT_DIR} DATASETS.NAMES "('your dataset name')"

Arguments

${1}: stride size for pure transformer, e.g. [16, 16], [14, 14], [12, 12]
${2}: whether using SIE with camera, True or False.
${3}: whether using SIE with view, True or False.
${4}: whether using JPM, True or False.
${5}: choose transformer type from 'vit_base_patch16_224_TransReID',(The structure of the deit is the same as that of the vit, and only need to change the imagenet pretrained model) 'vit_small_patch16_224_TransReID','deit_small_patch16_224_TransReID',
${OUTPUT_DIR}: folder for saving logs and checkpoints, e.g. ../logs/market1501

or you can directly train with following yml and commands:

# DukeMTMC transformer-based baseline
python train.py --config_file configs/DukeMTMC/vit_base.yml MODEL.DEVICE_ID "('0')"
# DukeMTMC baseline + JPM
python train.py --config_file configs/DukeMTMC/vit_jpm.yml MODEL.DEVICE_ID "('0')"
# DukeMTMC baseline + SIE
python train.py --config_file configs/DukeMTMC/vit_sie.yml MODEL.DEVICE_ID "('0')"
# DukeMTMC TransReID (baseline + SIE + JPM)
python train.py --config_file configs/DukeMTMC/vit_transreid.yml MODEL.DEVICE_ID "('0')"
# DukeMTMC TransReID with stride size [12, 12]
python train.py --config_file configs/DukeMTMC/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')"

# MSMT17
python train.py --config_file configs/MSMT17/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')"
# OCC_Duke
python train.py --config_file configs/OCC_Duke/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')"
# Market
python train.py --config_file configs/Market/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')"

Evaluation

python test.py --config_file 'choose which config to test' MODEL.DEVICE_ID "('your device id')" TEST.WEIGHT "('your path of trained checkpoints')"

Some examples:

# DukeMTMC
python test.py --config_file configs/DukeMTMC/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')"  TEST.WEIGHT '../logs/duke_vit_transreid/transformer_120.pth'
# MSMT17
python test.py --config_file configs/MSMT17/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')" TEST.WEIGHT '../logs/msmt17_vit_transreid/transformer_120.pth'
# OCC_Duke
python test.py --config_file configs/OCC_Duke/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')" TEST.WEIGHT '../logs/occ_duke_vit_transreid/transformer_120.pth'
# Market
python test.py --config_file configs/Market/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')"  TEST.WEIGHT '../logs/market_vit_transreid/transformer_120.pth'

Trained Models and logs (Size 256)

Model	MSMT17	Market	Duke	OCC_Duke	VeRi	VehicleID
baseline(ViT)	model \| log	model \| log	model \| log	model \| log	TBD	TBD
TransReID^*(ViT)	model \| log	model \| log	model \| log	model \| log	TBD	TBD
TransReID^*(DeiT)	model \| log	model \| log	model \| log	model \| log	TBD	TBD

（We reorganize the code. Now we are running each experiment one by one to make sure that you can reproduce the results in our paper. We will gradually upload the logs and models after training in the following weeks. Thanks for your attention.）

Acknowledgement

Codebase from reid-strong-baseline , pytorch-image-models

Citation

If you find this code useful for your research, please cite our paper

@article{he2021transreid,
  title={TransReID: Transformer-based Object Re-Identification},
  author={He, Shuting and Luo, Hao and Wang, Pichao and Wang, Fan and Li, Hao and Jiang, Wei},
  journal={arXiv preprint arXiv:2102.04378},
  year={2021}
}

Contact

If you have any question, please feel free to contact us. E-mail: [email protected] , [email protected]

TransReID: Transformer-based Object Re-Identification

Related tags

Overview

TransReID: Transformer-based Object Re-Identification [arxiv]

Pipeline

Abaltion Study of Transformer-based Strong Baseline

Requirements

Installation

Prepare Datasets

Prepare DeiT or ViT Pre-trained Models

Training

Arguments

Evaluation

Trained Models and logs (Size 256)

Acknowledgement

Citation

Contact

Owner

This code is 3d-CNN model that can predict environmental value

基于Paddle框架的arcface复现

Implementation of the paper ''Implicit Feature Refinement for Instance Segmentation''.

Learning with Noisy Labels via Sparse Regularization, ICCV2021

Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021

First-Order Probabilistic Programming Language

Convert Pytorch model to onnx or tflite, and the converted model can be visualized by Netron

MGFN: Multi-Graph Fusion Networks for Urban Region Embedding was accepted by IJCAI-2022.

Evaluating Cross-lingual Sentence Representations

BabelCalib: A Universal Approach to Calibrating Central Cameras. In ICCV (2021)

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and OpenVINO supported.

HMLLDB is a collection of LLDB commands to assist in the debugging of iOS apps.

The description of FMFCC-A (audio track of FMFCC) dataset and Challenge resluts.

A python module for scientific analysis of 3D objects based on VTK and Numpy

Rule Based Classification Project

OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion.

Towards Multi-Camera 3D Human Pose Estimation in Wild Environment

Sparse Physics-based and Interpretable Neural Networks

WRENCH: Weak supeRvision bENCHmark

[WWW 2022] Zero-Shot Stance Detection via Contrastive Learning