Metadata-Version: 2.1
Name: recstudio
Version: 0.0.1a3
Summary: A modular, efficient, unified, and comprehensive recommendation library based on PyTorch.
Home-page: https://github.com/ustcml/RecStudio
Author: USTCML
Author-email: liandefu@ustc.edu.cn
License: UNKNOWN
Platform: UNKNOWN
Classifier: License :: OSI Approved :: MIT License
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy (>=1.20.1)
Requires-Dist: torch (>=1.9.0)
Requires-Dist: scipy (>=1.6.0)
Requires-Dist: pandas (>=1.3.0)
Requires-Dist: tqdm (>=4.48.2)
Requires-Dist: colorlog (==4.7.2)
Requires-Dist: colorama (==0.4.4)
Requires-Dist: pyyaml (>=5.1.0)
Requires-Dist: tensorboard (>=2.5.0)
Requires-Dist: pytorch-lightning (==1.4.9)
Requires-Dist: nni (==2.6.1)

RecStudio is a modular, efficient, unified, and comprehensive recommendation library based on PyTorch.We divide all the models into 3 basic classes according to the number of towers: TowerFree, ItemTower, TwoTower, and cover models in 4 tasks: General Recommendation, Sequential Recommendation, Knowledge-based Recommendation, Social-Network-based Recommendation. View github page: https://github.com/ustcml/RecStudio

