Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/damo-cv/TransReID

[ICCV-2021] TransReID: Transformer-based Object Re-Identification
https://github.com/damo-cv/TransReID
Last synced: 3 months ago
JSON representation
[ICCV-2021] TransReID: Transformer-based Object Re-Identification
Host: GitHub
URL: https://github.com/damo-cv/TransReID
Owner: damo-cv
License: mit
Created: 2021-03-26T14:07:14.000Z (over 3 years ago)
Default Branch: main
Last Pushed: 2024-04-11T07:24:45.000Z (7 months ago)
Last Synced: 2024-06-12T01:13:18.672Z (5 months ago)
Language: Python
Homepage:
Size: 2.79 MB
Stars: 763
Watchers: 7
Forks: 174
Open Issues: 32
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project

Vehicle_reID-Collection - code
README

        ![Python >=3.5](https://img.shields.io/badge/Python->=3.5-yellow.svg)

![PyTorch >=1.0](https://img.shields.io/badge/PyTorch->=1.6-blue.svg)

# [ICCV2021] TransReID: Transformer-based Object Re-Identification [[pdf]](https://openaccess.thecvf.com/content/ICCV2021/papers/He_TransReID_Transformer-Based_Object_Re-Identification_ICCV_2021_paper.pdf)

The *official* repository for  [TransReID: Transformer-based Object Re-Identification](https://arxiv.org/abs/2102.04378) achieves state-of-the-art performances on object re-ID, including person re-ID and vehicle re-ID.

## News

- 🌟 2023.11 [VGSG](https://arxiv.org/abs/2311.07514.pdf) for Text-based Person Search is accepted to TIP. 

- 🌟 2023.9 [RGANet](https://arxiv.org/abs/2309.03558) for Occluded Person Re-identification is accepted to TIFS. 

- 2023.3 The general human representation pre-training model. [SOLIDER](https://github.com/tinyvision/SOLIDER)

- 2021.12 We improve TransReID via self-supervised pre-training. Please refer to [TransReID-SSL](https://github.com/michuanhaohao/TransReID-SSL)

- 2021.3  We release the code of TransReID.

## Pipeline

![framework](figs/framework.png)

## Abaltion Study of Transformer-based Strong Baseline

![framework](figs/ablation.png)

## Requirements

### Installation

```bash

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

```bash

mkdir data

```

Download the person datasets [Market-1501](https://drive.google.com/file/d/0B8-rUzbwVRk0c054eEozWG9COHM/view), [MSMT17](https://arxiv.org/abs/1711.08565), [DukeMTMC-reID](https://arxiv.org/abs/1609.01775),[Occluded-Duke](https://github.com/lightas/Occluded-DukeMTMC-Dataset), and the vehicle datasets [VehicleID](https://www.pkuml.org/resources/pku-vehicleid.html), [VeRi-776](https://github.com/JDAI-CV/VeRidataset), 

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](https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_224-80ecf9dd.pth), [ViT-Small](https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/vit_small_p16_224-15ec54c9.pth), [DeiT-Small](https://dl.fbaipublicfiles.com/deit/deit_small_distilled_patch16_224-649709d9.pth), [DeiT-Base](https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_224-df68dfff.pth)

## Training

We utilize 1  GPU for training.

```bash

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:**

```bash

# 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

```bash

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:**

```bash

# 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)

![framework](figs/sota.png)

DatasetsMSMT17MarketDukeOCC_DukeVeRiVehicleID

ModelmAP | R1mAP | R1mAP | R1mAP | R1mAP | R1R1 | R5Baseline(ViT)

  61.8 | 81.887.1 | 94.679.6 | 89.053.8 | 61.179.0 | 96.683.5 | 96.7  model | logmodel | logmodel | logmodel | logmodel | logmodel | testTransReID^*(ViT)

  67.8 | 85.389.0 | 95.182.2 | 90.759.5 | 67.482.1 | 97.485.2 | 97.4

  model | logmodel | logmodel | logmodel | logmodel | logmodel | testTransReID^*(DeiT)

  66.3 | 84.088.5 | 95.181.9 | 90.757.7 | 65.282.4 | 97.186.0 | 97.6

  model | logmodel | logmodel | logmodel | logmodel | logmodel | test

Note: We reorganize code and the performances are slightly different from the paper's.

## Acknowledgement

Codebase from [reid-strong-baseline](https://github.com/michuanhaohao/reid-strong-baseline) , [pytorch-image-models](https://github.com/rwightman/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]](mailto:[email protected]) , [[email protected]](mailto:[email protected])