Torchreid-Pip: Packaged version of Torchreid

This repo is a packaged version of the Torchreid algorithm.

Installation

pip install torchreid

Overview

1. Import `torchreid`

import torchreid

2. Load data manager

datamanager = torchreid.data.ImageDataManager(
    root="reid-data",
    sources="market1501",
    targets="market1501",
    height=256,
    width=128,
    batch_size_train=32,
    batch_size_test=100,
    transforms=["random_flip", "random_crop"]
)

3 Build model, optimizer and lr_scheduler

model = torchreid.models.build_model(
    name="resnet50",
    num_classes=datamanager.num_train_pids,
    loss="softmax",
    pretrained=True
)

model = model.cuda()

optimizer = torchreid.optim.build_optimizer(
    model,
    optim="adam",
    lr=0.0003
)

scheduler = torchreid.optim.build_lr_scheduler(
    optimizer,
    lr_scheduler="single_step",
    stepsize=20
)

4. Build engine

engine = torchreid.engine.ImageSoftmaxEngine(
    datamanager,
    model,
    optimizer=optimizer,
    scheduler=scheduler,
    label_smooth=True
)

5. Run training and test

engine.run(
    save_dir="log/resnet50",
    max_epoch=60,
    eval_freq=10,
    print_freq=10,
    test_only=False
)

Citation

If you use this code or the models in your research, please give credit to the following papers:

@article{torchreid,
    title={Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch},
    author={Zhou, Kaiyang and Xiang, Tao},
    journal={arXiv preprint arXiv:1910.10093},
    year={2019}
} 

@inproceedings{zhou2019osnet,
    title={Omni-Scale Feature Learning for Person Re-Identification},
    author={Zhou, Kaiyang and Yang, Yongxin and Cavallaro, Andrea and Xiang, Tao},
    booktitle={ICCV},
    year={2019}
}

@article{zhou2021osnet,
    title={Learning Generalisable Omni-Scale Representations for Person Re-Identification},
    author={Zhou, Kaiyang and Yang, Yongxin and Cavallaro, Andrea and Xiang, Tao},
    journal={TPAMI},
    year={2021}
}

Metadata

Release files for torchreid 0.2.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for torchreid 0.2.5
File	Size	Uploaded
torchreid-0.2.5.tar.gz	92.7 kB	Oct 16, 2022	Details

Release files / torchreid-0.2.5.tar.gz

Download URL	torchreid-0.2.5.tar.gz
Size	92.7 kB
Tags	Source
SHA-256 checksum How to use checksums	`bc1055c6fb8444968798708dd13fdad00148e9d7cf3cb18cf52f4b949857fe08`
BLAKE2b-256 checksum How to use checksums	`629ad3d8da1d1a8a189b2b2d6f191b21cd7fbdb91a587a9c992bcd9666895284`
Upload date	Oct 16, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.1 CPython/3.8.13`