TorchUtils:(WIP)TorchUtils是一个pytorch库,其中包含一些有用的工具和培训技巧-源码

上传者: 42144604 | 上传时间: 2021-03-10 18:06:35 | 文件大小: 40KB | 文件类型: ZIP
火炬工具 TorchUtils是一个pytorch库,其中包含几个有用的工具以及一些最新的培训方法或技巧。 (工作正在进行中) 待办事项:整理代码库 使用pytorch 1.6重新编写仓库(因为PyTorch 1.6现在支持许多工具功能或技巧) 进口 import torch_utils as tu 全部播种 SEED = 42 tu.tools.seed_everything(SEED) 数据扩充 去做: 比赛中使用的通用数据扩充 模型 建议的预训练模型: SEResNext-50 高效GPU swsl_ResNeXt EfficientNet_ns 混合网 网络 来自github仓库: 使用torch_utils快速构建模型: import timm model = timm.create_model('tresnet_m', pretrained=True) model

文件下载

资源详情

[{"title":"( 31 个子文件 40KB ) TorchUtils:(WIP)TorchUtils是一个pytorch库,其中包含一些有用的工具和培训技巧-源码","children":[{"title":"TorchUtils-master","children":[{"title":"__init__.py <span style='color:#111;'> 26B </span>","children":null,"spread":false},{"title":"torch_utils","children":[{"title":"models","children":[{"title":"mem_and_op_counter.py <span style='color:#111;'> 92B </span>","children":null,"spread":false},{"title":"lr_finder.py <span style='color:#111;'> 23.25KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 66B </span>","children":null,"spread":false},{"title":"model_summary.py <span style='color:#111;'> 4.77KB </span>","children":null,"spread":false}],"spread":true},{"title":"tools.py <span style='color:#111;'> 521B </span>","children":null,"spread":false},{"title":"advanced","children":[{"title":"dropblock.py <span style='color:#111;'> 4.88KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 52B </span>","children":null,"spread":false},{"title":"NextVLAD.py <span style='color:#111;'> 6.98KB </span>","children":null,"spread":false},{"title":"EMA.py <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false}],"spread":true},{"title":"dataset","children":[{"title":"common_aug.py <span style='color:#111;'> 2.21KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 202B </span>","children":null,"spread":false},{"title":"criterion","children":[{"title":"KLDLoss.py <span style='color:#111;'> 366B </span>","children":null,"spread":false},{"title":"circleloss.py <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"pytorch_loss.txt <span style='color:#111;'> 42B </span>","children":null,"spread":false},{"title":"label_smoothing.py <span style='color:#111;'> 2.89KB </span>","children":null,"spread":false},{"title":"segmentations","children":[{"title":"15种分割loss.txt <span style='color:#111;'> 591B </span>","children":null,"spread":false},{"title":"losses.py <span style='color:#111;'> 11.66KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"layers.py <span style='color:#111;'> 10.10KB </span>","children":null,"spread":false},{"title":"__version__.py <span style='color:#111;'> 62B </span>","children":null,"spread":false},{"title":"optimizer","children":[{"title":"radam.py <span style='color:#111;'> 7.88KB </span>","children":null,"spread":false},{"title":"group_optim.py <span style='color:#111;'> 1.50KB </span>","children":null,"spread":false},{"title":"gc.py <span style='color:#111;'> 10.45KB </span>","children":null,"spread":false},{"title":"over9000.py <span style='color:#111;'> 5.51KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 162B </span>","children":null,"spread":false},{"title":"lookahead.py <span style='color:#111;'> 2.44KB </span>","children":null,"spread":false},{"title":"ranger.py <span style='color:#111;'> 7.59KB </span>","children":null,"spread":false}],"spread":true},{"title":"lr_scheduler","children":[{"title":"onecycle.py <span style='color:#111;'> 2.86KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 112B </span>","children":null,"spread":false},{"title":"cosine_annealing_with_warmup.py <span style='color:#111;'> 2.71KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"README.md <span style='color:#111;'> 3.83KB </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