Customized Torchreid for pyppbox: Deep learning person re-identification.
Project description
Customized Torchreid for pyppbox
Torchreid is a library for deep-learning person re-identification using PyTorch.
pyppbox-torchreid is a customized of Torchreid for pyppbox and:
- Ensures that
Cythonnatively works on all OS platform (Windows/Linux), - Enables freedom of passing local model/weight files from anywhere,
- Disables some models which are not used in
pyppbox.
All source credit and more info -> Original KaiyangZhou's repo.
Install
Use Wheels fron releases or directly install from PyPI:
pip install pyppbox-torchreid
Or install from GitHub directly:
pip install git+https://github.com/rathaumons/torchreid-for-pyppbox.git
To be able to run, you must install OpenCV and PyTorch with GPU:
pip install opencv-contrib-python
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
Note: PyTorch doesn't support GUP on macOS.
Build from source
(Optional, auto install) Building Wheels or source distribution only requires these modules:
pip install "setuptools>=67.2.0"
pip install "Cython>=0.29.32"
pip install "numpy>=1.21.6"
Recommend using build for building both .whl and .tar.gz:
git clone https://github.com/rathaumons/torchreid-for-pyppbox/
cd torchreid-for-pyppbox
pip install wheel build
python -m build --sdist
python -m build --wheel
cd dist
After you install pyppbox-torchred, OpenCV and PyTorch, you can check if Cython rank_cy works:
cd pyppbox_torchreid/metrics/rank_cylib
python test_cython.py
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
File details
Details for the file pyppbox-torchreid-1.4.0.1.tar.gz.
File metadata
- Download URL: pyppbox-torchreid-1.4.0.1.tar.gz
- Upload date:
- Size: 92.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.11.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a409c7bb10275741c1aea1e6afaba9db72d16cc348e5ddb2843fab5a82e284d7
|
|
| MD5 |
2c66fab05472a905fd936b434772e81e
|
|
| BLAKE2b-256 |
e265704ff678f2fa8da25c6ebc0d3e4da92bd4a576881238dc70910891b046bc
|