co-mod-gan:[ICLR 2021,Spotlight]通过协同调制的生成对抗网络进行大规模图像完成-源码

上传者: 42165980 | 上传时间: 2021-06-29 20:43:14 | 文件大小: 8.58MB | 文件类型: ZIP
通过协同调制的对抗网络进行大规模图像完成,ICLR 2021(聚焦) | [NEW!]是时候玩我们的! 条件生成对抗网络的许多任务特定变体已经开发出来用于图像完成。 然而,仍然存在严重的局限性,即在处理大规模缺失区域时,所有现有算法都倾向于失败。 为了克服这一挑战,我们提出了一种通用的新方法,该方法通过对有条件和随机样式表示形式进行共调制来弥合图像条件和最近调制的无条件生成体系结构之间的差距。 此外,由于缺乏用于图像完成的良好定量指标,我们提出了新的配对/未配对初始判别分数(P-IDS / U-IDS) ,该指标可通过线性可分离性来可靠地测量修复图像与真实图像之间的感知保真度在特征空间中。 实验证明,在质量和多样性方面都优于最新形式的自由形式图像完成功能,并且易于将图像概括为图像到图像的翻译。 通过协同调制的对抗网络进行大规模图像完成,,盛怡伦,董悦,肖亮,张兆祥,徐彦清华大学与微软

文件下载

资源详情

[{"title":"( 40 个子文件 8.58MB ) co-mod-gan:[ICLR 2021,Spotlight]通过协同调制的生成对抗网络进行大规模图像完成-源码","children":[{"title":"co-mod-gan-master","children":[{"title":"dnnlib","children":[{"title":"submission","children":[{"title":"internal","children":[{"title":"local.py <span style='color:#111;'> 769B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 247B </span>","children":null,"spread":false}],"spread":true},{"title":"submit.py <span style='color:#111;'> 13.19KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 274B </span>","children":null,"spread":false},{"title":"run_context.py <span style='color:#111;'> 4.15KB </span>","children":null,"spread":false}],"spread":true},{"title":"util.py <span style='color:#111;'> 13.59KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 774B </span>","children":null,"spread":false},{"title":"tflib","children":[{"title":"custom_ops.py <span style='color:#111;'> 7.18KB </span>","children":null,"spread":false},{"title":"tfutil.py <span style='color:#111;'> 9.45KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 467B </span>","children":null,"spread":false},{"title":"ops","children":[{"title":"fused_bias_act.py <span style='color:#111;'> 8.34KB </span>","children":null,"spread":false},{"title":"upfirdn_2d.cu <span style='color:#111;'> 14.79KB </span>","children":null,"spread":false},{"title":"fused_bias_act.cu <span style='color:#111;'> 7.61KB </span>","children":null,"spread":false},{"title":"upfirdn_2d.py <span style='color:#111;'> 16.27KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 235B </span>","children":null,"spread":false}],"spread":true},{"title":"autosummary.py <span style='color:#111;'> 7.85KB </span>","children":null,"spread":false},{"title":"network.py <span style='color:#111;'> 29.28KB </span>","children":null,"spread":false},{"title":"optimizer.py <span style='color:#111;'> 17.55KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"metrics","children":[{"title":"learned_perceptual_image_patch_similarity.py <span style='color:#111;'> 2.71KB </span>","children":null,"spread":false},{"title":"frechet_inception_distance.py <span style='color:#111;'> 3.75KB </span>","children":null,"spread":false},{"title":"metric_defaults.py <span style='color:#111;'> 5.13KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 235B </span>","children":null,"spread":false},{"title":"inception_discriminative_score.py <span style='color:#111;'> 3.94KB </span>","children":null,"spread":false},{"title":"metric_base.py <span style='color:#111;'> 8.66KB </span>","children":null,"spread":false}],"spread":true},{"title":"run_metrics.py <span style='color:#111;'> 3.52KB </span>","children":null,"spread":false},{"title":"training","children":[{"title":"loss.py <span style='color:#111;'> 2.27KB </span>","children":null,"spread":false},{"title":"dataset.py <span style='color:#111;'> 13.50KB </span>","children":null,"spread":false},{"title":"misc.py <span style='color:#111;'> 5.84KB </span>","children":null,"spread":false},{"title":"co_mod_gan.py <span style='color:#111;'> 27.94KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 235B </span>","children":null,"spread":false},{"title":"mask_generator.py <span style='color:#111;'> 3.45KB </span>","children":null,"spread":false},{"title":"training_loop.py <span style='color:#111;'> 20.51KB </span>","children":null,"spread":false}],"spread":true},{"title":"run_demo.py <span style='color:#111;'> 6.31KB </span>","children":null,"spread":false},{"title":"Dockerfile <span style='color:#111;'> 426B </span>","children":null,"spread":false},{"title":"imgs","children":[{"title":"demo.gif <span style='color:#111;'> 8.00MB </span>","children":null,"spread":false},{"title":"grid-main.jpg <span style='color:#111;'> 599.26KB </span>","children":null,"spread":false}],"spread":true},{"title":".gitignore <span style='color:#111;'> 137B </span>","children":null,"spread":false},{"title":"run_training.py <span style='color:#111;'> 5.79KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 5.70KB </span>","children":null,"spread":false},{"title":"LICENSE.txt <span style='color:#111;'> 5.96KB </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