Torchreid is a library for deep-learning person re-identification, written in PyTorch and developed for our ICCV’19 project, Omni-Scale Feature Learning for Person Re-Identification. In "deep-person-reid/scripts/", we provide a unified interface to train and test a model. See "scripts/main.py" and "scripts/default_config.py" for more details. The folder "configs/" contains some predefined configs which you can use as a starting point. The code will automatically (download and) load the ImageNet pretrained weights. After the training is done, the model will be saved as "log/osnet_x1_0_market1501_softmax_cosinelr/model.pth.tar-250". Under the same folder, you can find the tensorboard file. Different from the same-domain setting, here we replace random_erase with color_jitter. This can improve the generalization performance on the unseen target dataset.

Features

  • Multi-GPU training
  • Support both image- and video-reid
  • End-to-end training and evaluation
  • Incredibly easy preparation of reid datasets
  • Multi-dataset training
  • Cross-dataset evaluation
  • Standard protocol used by most research papers

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow Torchreid

Torchreid Web Site

Other Useful Business Software
Get the most trusted enterprise browser Icon
Get the most trusted enterprise browser

Advanced built-in security helps IT prevent breaches before they happen

Defend against security incidents with Chrome Enterprise. Create customizable controls, manage extensions and set proactive alerts to keep your data and employees protected without slowing down productivity.
Download Chrome
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Torchreid!

Additional Project Details

Operating Systems

Windows

Programming Language

Python

Related Categories

Python Machine Learning Software, Python Deep Learning Frameworks

Registered

2022-08-04