文件名称:CoMatch:配对代码
文件大小:452KB
文件格式:ZIP
更新时间:2024-06-09 03:51:58
semi-supervised-learning representation-learning self-supervised-learning contrastive-learning Python
CoMatch:具有对比图正则化的半监督学习(Salesforce研究) 这是的PyTorch实现: @article{CoMatch, title={Semi-supervised Learning with Contrastive Graph Regularization}, author={Junnan Li and Caiming Xiong and Steven C.H. Hoi}, journal={arXiv preprint arXiv:2011.11183}, year={2020} } 要求: PyTorch≥1.4 点安装tensorboard_logger 下载并将其提取到./data/ 要在CIFAR-10上执行半监督学习,每个班级有4个标签,请运行: python Train_CoMatch.py --n-labeled 40 --seed
【文件预览】:
CoMatch-main
----comatch.gif(427KB)
----LICENSE.txt(1KB)
----Train_CoMatch.py(15KB)
----utils.py(4KB)
----imagenet()
--------Train_CoMatch.py(23KB)
--------README.md(988B)
--------Model.py(9KB)
--------resnet.py(7KB)
--------loader.py(478B)
----datasets()
--------transform.py(2KB)
--------randaugment.py(9KB)
--------__init__.py(0B)
--------cifar.py(8KB)
--------sampler.py(8KB)
----Train_fixmatch.py(12KB)
----README.md(1KB)
----SECURITY.md(401B)
----CODE_OF_CONDUCT.md(5KB)
----WideResNet.py(8KB)