contrastive-learning:对比学习方法-源码

上传者: 42134554 | 上传时间: 2021-09-13 14:15:07 | 文件大小: 27KB | 文件类型: ZIP
对比学习方法 支持更多内容的对比学习方法的第三方pytorch实现(请参阅“可用内容”部分)。 有什么可用的? 使用SimCLR进行对比学习预训练 通过停止梯度进行在线线性评估 Pytorch闪电登录和默认收益(多GPU训练,混合精度等) 在GPU装置上收集负片以模拟更大的批次大小(尽管梯度不会在GPU上流动) 使用加快数据加载速度(以使用更多GPU内存为代价) SimCLR多分辨率农作物 SimCLR + 预训练后线性评估(通常得出1-1.5%的准确度点) 工作于: 结果 模型 方法 数据集 时代 批 温度 多作 大理 监督下 在线线性评估 预训练后线性评估 Resnet18 SimCLR Imagenet-100 100 256 0.2 70.74 71.02 Resnet18 SimCLR Imagenet-100 100 256 0.2 :check_mark_button:

文件下载

资源详情

[{"title":"( 25 个子文件 27KB ) contrastive-learning:对比学习方法-源码","children":[{"title":"contrastive-learning-main","children":[{"title":"utils","children":[{"title":"barlow_twins_loss.py <span style='color:#111;'> 421B </span>","children":null,"spread":false},{"title":"classification_dataloader.py <span style='color:#111;'> 5.14KB </span>","children":null,"spread":false},{"title":"epoch_checkpointer.py <span style='color:#111;'> 1.54KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"metrics.py <span style='color:#111;'> 816B </span>","children":null,"spread":false},{"title":"contrastive_dataloader.py <span style='color:#111;'> 11.46KB </span>","children":null,"spread":false},{"title":"gather_layer.py <span style='color:#111;'> 898B </span>","children":null,"spread":false},{"title":"info_nce.py <span style='color:#111;'> 2.12KB </span>","children":null,"spread":false},{"title":"dali_dataloader.py <span style='color:#111;'> 8.44KB </span>","children":null,"spread":false}],"spread":true},{"title":"models","children":[{"title":"simclr.py <span style='color:#111;'> 5.41KB </span>","children":null,"spread":false},{"title":"base.py <span style='color:#111;'> 4.25KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"linear.py <span style='color:#111;'> 3.41KB </span>","children":null,"spread":false},{"title":"barlow_twins.py <span style='color:#111;'> 2.55KB </span>","children":null,"spread":false},{"title":"resnet.py <span style='color:#111;'> 8.69KB </span>","children":null,"spread":false},{"title":"dali.py <span style='color:#111;'> 6.42KB </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 144B </span>","children":null,"spread":false},{"title":"main_contrastive.py <span style='color:#111;'> 6.35KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"main_linear.py <span style='color:#111;'> 5.38KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.26KB </span>","children":null,"spread":false},{"title":"bash_files","children":[{"title":"run_linear.sh <span style='color:#111;'> 511B </span>","children":null,"spread":false},{"title":"run_contrastive.sh <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false},{"title":"run_barlow.sh <span style='color:#111;'> 473B </span>","children":null,"spread":false}],"spread":true},{"title":".gitignore <span style='color:#111;'> 2.09KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明