SMSR:[CVPR 2021]探索图像超分辨率中的稀疏性以进行有效推理

上传者: 42138716 | 上传时间: 2022-04-15 07:31:45 | 文件大小: 6.82MB | 文件类型: ZIP
SMSR Pytorch实施“探索图像超分辨率中的稀疏性以进行有效推理”,CVPR 2021 强调 在细粒度级别上查找和跳过SR网络中的冗余计算,以进行有效的推理。 通过显着降低FLOP并加快移动设备的速度来保持最先进的性能。 基于原始Pytorch API的稀疏卷积的有效实现,可更轻松地进行迁移和部署。 动机 网络架构 稀疏卷积的实现 为了更轻松地进行迁移和部署,我们使用基于原始Pytorch API的有效稀疏卷积实现,而不是通常基于CUDA的实现。 具体来说,首先从输入中提取稀疏特征,如下图所示。 然后,执行矩阵乘法以产生输出特征。 要求 Python 3.6 PyTorch == 1.1.0 麻木 skimage 意象 matplotlib cv2 火车 1.准备训练数据 1.1从或下载DIV2K训练数据(800个训练+ 100个验证图像)。 1.2根据HR和LR图像

文件下载

资源详情

[{"title":"( 41 个子文件 6.82MB ) SMSR:[CVPR 2021]探索图像超分辨率中的稀疏性以进行有效推理","children":[{"title":"SMSR-master","children":[{"title":"Figs","children":[{"title":"sparse conv.png <span style='color:#111;'> 137.48KB </span>","children":null,"spread":false},{"title":"real.png <span style='color:#111;'> 292.90KB </span>","children":null,"spread":false},{"title":"overview.png <span style='color:#111;'> 69.94KB </span>","children":null,"spread":false},{"title":"sparsity.png <span style='color:#111;'> 340.08KB </span>","children":null,"spread":false},{"title":"implementation.png <span style='color:#111;'> 108.12KB </span>","children":null,"spread":false},{"title":"Urban100.png <span style='color:#111;'> 980.90KB </span>","children":null,"spread":false},{"title":"visualization.png <span style='color:#111;'> 48.28KB </span>","children":null,"spread":false},{"title":"results.png <span style='color:#111;'> 264.27KB </span>","children":null,"spread":false},{"title":"visualization2.png <span style='color:#111;'> 84.40KB </span>","children":null,"spread":false}],"spread":true},{"title":"loss","children":[{"title":"adversarial.py <span style='color:#111;'> 3.24KB </span>","children":null,"spread":false},{"title":"vgg.py <span style='color:#111;'> 1.07KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 6.09KB </span>","children":null,"spread":false},{"title":"discriminator.py <span style='color:#111;'> 1.26KB </span>","children":null,"spread":false}],"spread":true},{"title":"experiment","children":[{"title":"SMSR_X2","children":[{"title":"model","children":[{"title":"model_1000.pt <span style='color:#111;'> 3.79MB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"dataloader.py <span style='color:#111;'> 4.67KB </span>","children":null,"spread":false},{"title":"model","children":[{"title":"smsr.py <span style='color:#111;'> 14.50KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 6.29KB </span>","children":null,"spread":false},{"title":"common.py <span style='color:#111;'> 2.75KB </span>","children":null,"spread":false}],"spread":true},{"title":"main.py <span style='color:#111;'> 620B </span>","children":null,"spread":false},{"title":"option.py <span style='color:#111;'> 6.69KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.34KB </span>","children":null,"spread":false},{"title":"utility.py <span style='color:#111;'> 8.02KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":"div2k.py <span style='color:#111;'> 707B </span>","children":null,"spread":false},{"title":"multiscalesrdata.py <span style='color:#111;'> 7.05KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1.21KB </span>","children":null,"spread":false},{"title":"demo.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"benchmark.py <span style='color:#111;'> 699B </span>","children":null,"spread":false},{"title":"srdata.py <span style='color:#111;'> 7.01KB </span>","children":null,"spread":false},{"title":"common.py <span style='color:#111;'> 2.04KB </span>","children":null,"spread":false}],"spread":true},{"title":"testsets","children":[{"title":"benchmark","children":[{"title":"Set5","children":[{"title":"LR_bicubic","children":[{"title":"X2","children":[{"title":"bird.png <span style='color:#111;'> 37.36KB </span>","children":null,"spread":false},{"title":"woman.png <span style='color:#111;'> 35.76KB </span>","children":null,"spread":false},{"title":"baby.png <span style='color:#111;'> 106.95KB </span>","children":null,"spread":false},{"title":"butterfly.png <span style='color:#111;'> 35.08KB </span>","children":null,"spread":false},{"title":"head.png <span style='color:#111;'> 32.35KB </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":"HR","children":[{"title":"bird.png <span style='color:#111;'> 117.63KB </span>","children":null,"spread":false},{"title":"woman.png <span style='color:#111;'> 116.06KB </span>","children":null,"spread":false},{"title":"baby.png <span style='color:#111;'> 362.56KB </span>","children":null,"spread":false},{"title":"butterfly.png <span style='color:#111;'> 124.54KB </span>","children":null,"spread":false},{"title":"head.png <span style='color:#111;'> 111.12KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"template.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"trainer.py <span style='color:#111;'> 7.17KB </span>","children":null,"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