[ICCV2021] TransReID: Transformer-based Object Re-Identification [pdf]
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.
News
- 2021.12 We improve TransReID via self-supervised pre-training. Please refer to TransReID-SSL
- 2021.3 We release the code of TransReID.
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')"
# VeRi
python train.py --config_file configs/VeRi/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')"
# VehicleID (The dataset is large and we utilize 4 v100 GPUs for training )
CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 --master_port 66666 train.py --config_file configs/VehicleID/vit_transreid_stride.yml MODEL.DIST_TRAIN True
# or using following commands:
Bash dist_train.sh
Tips: For person datasets with size 256x128, TransReID with stride occupies 12GB GPU memory and TransReID occupies 7GB GPU memory.
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_stride/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_stride/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_stride/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_stride/transformer_120.pth'
# VeRi
python test.py --config_file configs/VeRi/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')" TEST.WEIGHT '../logs/veri_vit_transreid_stride/transformer_120.pth'
# VehicleID (We test 10 times and get the final average score to avoid randomness)
python test.py --config_file configs/VehicleID/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')" TEST.WEIGHT '../logs/vehicleID_vit_transreid_stride/transformer_120.pth'
Trained Models and logs (Size 256)
| Datasets | MSMT17 | Market | Duke | OCC_Duke | VeRi | VehicleID |
|---|---|---|---|---|---|---|
| Model | mAP | R1 | mAP | R1 | mAP | R1 | mAP | R1 | mAP | R1 | R1 | R5 |
| Baseline(ViT) | 61.8 | 81.8 | 87.1 | 94.6 | 79.6 | 89.0 | 53.8 | 61.1 | 79.0 | 96.6 | 83.5 | 96.7 |
| model | log | model | log | model | log | model | log | model | log | model | test | |
| TransReID*(ViT) | 67.8 | 85.3 | 89.0 | 95.1 | 82.2 | 90.7 | 59.5 | 67.4 | 82.1 | 97.4 | 85.2 | 97.4 |
| model | log | model | log | model | log | model | log | model | log | model | test | |
| TransReID*(DeiT) | 66.3 | 84.0 | 88.5 | 95.1 | 81.9 | 90.7 | 57.7 | 65.2 | 82.4 | 97.1 | 86.0 | 97.6 |
| model | log | model | log | model | log | model | log | model | log | model | test |
Note: We reorganize code and the performances are slightly different from the paper's.
Acknowledgement
Codebase from reid-strong-baseline , pytorch-image-models
We import veri776 viewpoint label from repo: https://github.com/Zhongdao/VehicleReIDKeyPointData
Citation
If you find this code useful for your research, please cite our paper
@InProceedings{He_2021_ICCV,
author = {He, Shuting and Luo, Hao and Wang, Pichao and Wang, Fan and Li, Hao and Jiang, Wei},
title = {TransReID: Transformer-Based Object Re-Identification},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2021},
pages = {15013-15022}
}
Contact
If you have any question, please feel free to contact us. E-mail: [email protected] , [email protected]
29 Nov 30, 2022
11 Nov 3, 2022
37 Dec 15, 2022
75 Dec 16, 2022
26 Dec 26, 2022
8 Apr 16, 2022
85 Dec 7, 2022
84 Dec 12, 2022
91 Dec 30, 2022
36 Dec 5, 2022
54 Dec 22, 2022
80 Dec 25, 2022
84 Dec 26, 2022
1 Dec 25, 2021
32 Apr 4, 2022
45 Dec 25, 2022
348 Jan 5, 2023
409 Jan 6, 2023
225 Nov 13, 2022