efficientdet:PyTorch用于对象检测的最新模型的实现EfficientDet [已提供预训练权重]

上传者: 42116791 | 上传时间: 2022-04-06 21:17:04 | 文件大小: 1.24MB | 文件类型: ZIP
EfficientDet:可扩展且高效的对象检测 最新对象检测架构EfficientDet的PyTorch实现 动机 截至我开始从事该项目时,GitHub上没有PyTorch实施与该模型参数的数量与原始论文相匹配。 所有现有的存储库都与最近发布的TensorFlow实施方式发生了很大的变化(例如,更改主干的步幅,缺少批处理规范化层,池化层中没有“相同”的填充策略,不同的训练超参数,不使用指数移动平均衰减等)。 这是我在PyTorch中重现EfficientDet的尝试。 我的最终目标是从原始论文复制训练周期并获得几乎相同的结果。 实施注意事项 除了TensorFlow实现之外,我还消除了卷积层中无用的偏差,然后进行了批量归一化,这导致了参数减少。 模型动物园 型号名称 重物 #params #params纸 肺动脉压 val mAP纸 D0 38.78万 390万 32.8 33.5

文件下载

资源详情

[{"title":"( 33 个子文件 1.24MB ) efficientdet:PyTorch用于对象检测的最新模型的实现EfficientDet [已提供预训练权重]","children":[{"title":"efficientdet-master","children":[{"title":"log","children":[{"title":"logger.py <span style='color:#111;'> 780B </span>","children":null,"spread":false}],"spread":true},{"title":"main.py <span style='color:#111;'> 3.39KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":".gitignore <span style='color:#111;'> 5B </span>","children":null,"spread":false}],"spread":true},{"title":"model","children":[{"title":"head.py <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false},{"title":"module.py <span style='color:#111;'> 4.33KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 30B </span>","children":null,"spread":false},{"title":"efficientnet","children":[{"title":"utils.py <span style='color:#111;'> 13.82KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 57B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 106B </span>","children":null,"spread":false},{"title":"efficientnet.py <span style='color:#111;'> 10.21KB </span>","children":null,"spread":false}],"spread":true},{"title":"det.py <span style='color:#111;'> 4.26KB </span>","children":null,"spread":false},{"title":"bifpn.py <span style='color:#111;'> 3.95KB </span>","children":null,"spread":false},{"title":"backbone.py <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false}],"spread":true},{"title":"train.py <span style='color:#111;'> 1.79KB </span>","children":null,"spread":false},{"title":"dataloader.py <span style='color:#111;'> 3.80KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"validation.py <span style='color:#111;'> 2.34KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 129B </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 2.74KB </span>","children":null,"spread":false},{"title":"demo","children":[{"title":"test_params.py <span style='color:#111;'> 798B </span>","children":null,"spread":false},{"title":"demonstration.ipynb <span style='color:#111;'> 1.59MB </span>","children":null,"spread":false},{"title":"coco_val_results.txt <span style='color:#111;'> 4.03KB </span>","children":null,"spread":false}],"spread":true},{"title":"weights","children":[{"title":".gitignore <span style='color:#111;'> 5B </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 3.53KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"transforms.py <span style='color:#111;'> 5.97KB </span>","children":null,"spread":false},{"title":"tools.py <span style='color:#111;'> 6.62KB </span>","children":null,"spread":false},{"title":"processing.py <span style='color:#111;'> 2.45KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 4.81KB </span>","children":null,"spread":false},{"title":"anchors.py <span style='color:#111;'> 12.87KB </span>","children":null,"spread":false},{"title":"visual.py <span style='color:#111;'> 3.72KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 174B </span>","children":null,"spread":false},{"title":"wrapper.py <span style='color:#111;'> 2.48KB </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"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