Self-Guided-Network-for-Fast-Image-Denoising:ICCV 2019论文SGN的PyTorch实施

上传者: 42160425 | 上传时间: 2022-12-15 22:52:09 | 文件大小: 2.47MB | 文件类型: ZIP
自导网络快速图像去噪 SGN的PyTorch实现以及给定噪声范围的估计PSNR 训练 我在Python 3.6和PyTorch 1.0环境上训练了此SGN。 培训策略与论文相同。 您可以使用以下脚本对自己的数据进行训练(请注意,您需要修改数据集路径): cd SGN python train.py or sh zyz.sh 测验 我使用ILSVRC2012验证集对4个NVIDIA TITAN Xp GPU进行了培训,并在1个TITAN Xp GPU上进行了测试。 详细信息显示在代码train.py 。 该演示来自SGN的ILSVRC2012验证集(mu = 0,sigma = 30,batchsize = 32、1000000次迭代)。 左:干净的图像(从COCO2014验证集中选择,COCO_val2014_000000264615.jpg) 中:加性高斯噪声+清晰图像 右

文件下载

资源详情

[{"title":"( 32 个子文件 2.47MB ) Self-Guided-Network-for-Fast-Image-Denoising:ICCV 2019论文SGN的PyTorch实施","children":[{"title":"Self-Guided-Network-for-Fast-Image-Denoising-master","children":[{"title":"SGN","children":[{"title":"trainer.py <span style='color:#111;'> 4.61KB </span>","children":null,"spread":false},{"title":"validation.py <span style='color:#111;'> 5.76KB </span>","children":null,"spread":false},{"title":"PixelUnShuffle.py <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":"validation_folder.py <span style='color:#111;'> 3.98KB </span>","children":null,"spread":false},{"title":"network.py <span style='color:#111;'> 7.18KB </span>","children":null,"spread":false},{"title":"PixelUnShuffle_example.py <span style='color:#111;'> 477B </span>","children":null,"spread":false},{"title":"network_test.py <span style='color:#111;'> 1.46KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 2.39KB </span>","children":null,"spread":false},{"title":"test.py <span style='color:#111;'> 2.84KB </span>","children":null,"spread":false},{"title":"dataset.py <span style='color:#111;'> 4.06KB </span>","children":null,"spread":false},{"title":"network_module.py <span style='color:#111;'> 7.48KB </span>","children":null,"spread":false},{"title":"zyz.sh <span style='color:#111;'> 550B </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 5.11KB </span>","children":null,"spread":false}],"spread":false},{"title":"result.jpg <span style='color:#111;'> 116.68KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.26KB </span>","children":null,"spread":false},{"title":"noisy_img_examples","children":[{"title":"0.0075.png <span style='color:#111;'> 155.39KB </span>","children":null,"spread":false},{"title":"0.05.png <span style='color:#111;'> 160.78KB </span>","children":null,"spread":false},{"title":"0.01.png <span style='color:#111;'> 129.64KB </span>","children":null,"spread":false},{"title":"0.005.png <span style='color:#111;'> 111.52KB </span>","children":null,"spread":false},{"title":"0.001.png <span style='color:#111;'> 89.85KB </span>","children":null,"spread":false},{"title":"0.04.png <span style='color:#111;'> 149.77KB </span>","children":null,"spread":false},{"title":"0.02.png <span style='color:#111;'> 176.32KB </span>","children":null,"spread":false},{"title":"0.12.png <span style='color:#111;'> 165.10KB </span>","children":null,"spread":false},{"title":"0.18.png <span style='color:#111;'> 190.61KB </span>","children":null,"spread":false},{"title":"0.03.png <span style='color:#111;'> 142.11KB </span>","children":null,"spread":false},{"title":"0.2.png <span style='color:#111;'> 188.86KB </span>","children":null,"spread":false},{"title":"0.075.png <span style='color:#111;'> 175.98KB </span>","children":null,"spread":false},{"title":"0.15.png <span style='color:#111;'> 189.87KB </span>","children":null,"spread":false},{"title":"0.1.png <span style='color:#111;'> 176.61KB </span>","children":null,"spread":false},{"title":"0.3.png <span style='color:#111;'> 191.37KB </span>","children":null,"spread":false}],"spread":false},{"title":"noise_estimate.py <span style='color:#111;'> 4.35KB </span>","children":null,"spread":false},{"title":"noise_visualization.py <span style='color:#111;'> 3.38KB </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