DeLF-pytorch:PyTorch实现的“具有深深的局部特征的大规模图像检索”-源码

上传者: 42121058 | 上传时间: 2021-09-26 15:38:34 | 文件大小: 8.58MB | 文件类型: ZIP
深度局部特征(DeLF)的Pytorch实现 PyTorch实现的“具有深深的局部特征的大规模图像检索” 参考: : 先决条件 火炬 python3 CUDA 训练DeLF DeLF训练有两个步骤:(1)调整阶段,和(2)关键点阶段。 Finetune阶段加载ImageNet上预训练的resnet50模型,并进行优化。 关键点阶段将冻结“基本”网络,并且仅更新“注意”网络以进行关键点选择。 训练过程完成后,模型将保存在repo//keypoint/ckpt (1)培训微调阶段: $ cd train/ $ python main.py \ --stage ' finetune ' \ --optim ' sgd ' \ --gpu_id 6 \ --expr ' landmark ' \ --ncls 586 \ --f

文件下载

资源详情

[{"title":"( 29 个子文件 8.58MB ) DeLF-pytorch:PyTorch实现的“具有深深的局部特征的大规模图像检索”-源码","children":[{"title":"DeLF-pytorch-master","children":[{"title":"train","children":[{"title":"main.py <span style='color:#111;'> 3.45KB </span>","children":null,"spread":false},{"title":"dataloader.py <span style='color:#111;'> 3.12KB </span>","children":null,"spread":false},{"title":"delf.py <span style='color:#111;'> 10.18KB </span>","children":null,"spread":false},{"title":"solver.py <span style='color:#111;'> 8.21KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 7B </span>","children":null,"spread":false},{"title":"layers.py <span style='color:#111;'> 3.15KB </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 4.85KB </span>","children":null,"spread":false}],"spread":true},{"title":"notebook","children":[{"title":"visualize.ipynb <span style='color:#111;'> 7.23MB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"static","children":[{"title":"ldmk.png <span style='color:#111;'> 704.42KB </span>","children":null,"spread":false},{"title":"glr1k.png <span style='color:#111;'> 671.06KB </span>","children":null,"spread":false},{"title":"attn.png <span style='color:#111;'> 221.72KB </span>","children":null,"spread":false},{"title":"vis.png <span style='color:#111;'> 928.58KB </span>","children":null,"spread":false},{"title":"glr2k.png <span style='color:#111;'> 671.75KB </span>","children":null,"spread":false}],"spread":true},{"title":"extract","children":[{"title":"extractor.py <span style='color:#111;'> 15.31KB </span>","children":null,"spread":false},{"title":"pca.py <span style='color:#111;'> 1.78KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 21B </span>","children":null,"spread":false},{"title":"folder.py <span style='color:#111;'> 5.87KB </span>","children":null,"spread":false},{"title":".ipynb_checkpoints","children":[{"title":"visualize-checkpoint.ipynb <span style='color:#111;'> 24.67KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 1.96KB </span>","children":null,"spread":false}],"spread":true},{"title":".gitignore <span style='color:#111;'> 435B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 8.10KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"logger.py <span style='color:#111;'> 4.29KB </span>","children":null,"spread":false},{"title":"misc.py <span style='color:#111;'> 1.68KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 231B </span>","children":null,"spread":false}],"spread":true},{"title":"helper","children":[{"title":"feeder.py <span style='color:#111;'> 5.33KB </span>","children":null,"spread":false},{"title":"matcher.py <span style='color:#111;'> 4.98KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 78B </span>","children":null,"spread":false},{"title":"delf_helper.py <span style='color:#111;'> 14.61KB </span>","children":null,"spread":false}],"spread":true}],"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