Skip to content

Latest commit

 

History

History
130 lines (93 loc) · 5.32 KB

README.md

File metadata and controls

130 lines (93 loc) · 5.32 KB
Raw

Python >=3.5 PyTorch >=1.0

Swin ReID: Swin Transformer-based Object Re-Identification

Pipeline

image

Requirements

Installation

Please refer to TransReID.

pip install -r requirements.txt

(we use /torch 1.7.1 /torchvision 0.8.2 /timm 0.3.2 /cuda 11.7 /  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

The ImageNet pretrained swin transformer model: [Swin-base]https://drive.google.com/file/d/1ESQNMrZUsqqboym5GtKeV9L4-m8dpcAr/view?usp=sharing

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 TransReID (baseline + SIE + JPM)
python train.py --config_file configs/DukeMTMC/vit_transreid_stride.yml MODEL.DEVICE_ID "('0')"
# DukeMTMC Swin TransReID with stride size [12, 12] (baseline)
python train.py --config_file configs/DukeMTMC/swin_transreid_stride.yml MODEL.DEVICE_ID "('0')"

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

Tips: For person datasets with size 256x128, Swin TransReID with stride occupies 12GB 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'

Acknowledgement

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

If you find this code useful for your research, please cite TransReID.

Citation

@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}
}