neural-ode-metasolver:论文“神经微分方程的元求解器”的补充代码https-源码

上传者: 42122340 | 上传时间: 2021-07-14 13:40:46 | 文件大小: 10.53MB | 文件类型: ZIP
神经常微分方程的元解法 使用参数化求解器实现鲁棒的神经ODE。 大意 每个具有s级且为p阶的Runge-Kutta(RK)求解器均由一个系数表( Butcher tableau )定义。 对于s=p=2 , s=p=3和s=p=4 ,表中的所有系数都可以使用不超过两个变量的参数设置[1]。 通常,在神经ODE训练期间,使用具有固定Butcher表的RK解算器,并且仅训练右侧(RHS)功能。 我们建议使用RK解算器的整个参数族来提高神经ODE的鲁棒性。 要求 pytorch == 1.7 顶点== 0.1(用于训练) 例子 对于CIFAR-10和MNIST演示,请检查examples文件夹。 元求解器制度 在笔记本examples/cifar10/Evaluate model.ipynb我们展示了如何使用不同类型的Meta Solver机制(即: 单机版 解算器切换/平滑 求解器集成

文件下载

资源详情

[{"title":"( 55 个子文件 10.53MB ) neural-ode-metasolver:论文“神经微分方程的元求解器”的补充代码https-源码","children":[{"title":"neural-ode-metasolver-master","children":[{"title":"MegaAdversarial","children":[{"title":"src","children":[{"title":"attacks","children":[{"title":"base.py <span style='color:#111;'> 225B </span>","children":null,"spread":false},{"title":"fgsm.py <span style='color:#111;'> 5.45KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 111B </span>","children":null,"spread":false},{"title":"attack.py <span style='color:#111;'> 853B </span>","children":null,"spread":false},{"title":"pgd.py <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 37B </span>","children":null,"spread":false}],"spread":true},{"title":"examples","children":[{"title":"cifar10","children":[{"title":"checkpoints","children":[{"title":"fgsm_random_8_255_smoothing_00125.pth <span style='color:#111;'> 5.16MB </span>","children":null,"spread":false},{"title":"fgsm_random_8_255.pth <span style='color:#111;'> 5.16MB </span>","children":null,"spread":false},{"title":"accuracy","children":[{"title":"fgsm_random_8_255_clean.pkl <span style='color:#111;'> 673B </span>","children":null,"spread":false},{"title":"fgsm_random_8_255_smoothing_00125_pgd_8_255_2_255_7.pkl <span style='color:#111;'> 673B </span>","children":null,"spread":false},{"title":"fgsm_random_8_255_smoothing_00125_fgsm_8_255.pkl <span style='color:#111;'> 673B </span>","children":null,"spread":false},{"title":"fgsm_random_8_255_fgsm_8_255.pkl <span style='color:#111;'> 673B </span>","children":null,"spread":false},{"title":"fgsm_random_8_255_smoothing_00125_clean.pkl <span style='color:#111;'> 673B </span>","children":null,"spread":false},{"title":"fgsm_random_8_255_pgd_8_255_2_255_7.pkl <span style='color:#111;'> 673B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"train_and_attack.py <span style='color:#111;'> 25.36KB </span>","children":null,"spread":false},{"title":"Build the model.ipynb <span style='color:#111;'> 7.12KB </span>","children":null,"spread":false},{"title":"assets","children":[{"title":"fgsm_random_train_pgd_eps_8_255_lr_2_255_iters_7_test.png <span style='color:#111;'> 24.92KB </span>","children":null,"spread":false},{"title":"fgsm_random_train_clean_test.png <span style='color:#111;'> 21.49KB </span>","children":null,"spread":false},{"title":"fgsm_random_train_fgsm_eps_8_255_test.png <span style='color:#111;'> 20.80KB </span>","children":null,"spread":false}],"spread":true},{"title":"Evaluate the model.ipynb <span style='color:#111;'> 22.82KB </span>","children":null,"spread":false}],"spread":true},{"title":"mnist","children":[{"title":"checkpoints","children":[{"title":"checkpoint_15444.pth <span style='color:#111;'> 828.02KB </span>","children":null,"spread":false}],"spread":true},{"title":"train_and_attack.py <span style='color:#111;'> 13.87KB </span>","children":null,"spread":false},{"title":"Build the model.ipynb <span style='color:#111;'> 3.72KB </span>","children":null,"spread":false},{"title":"assets","children":[{"title":"mnist_adv.png <span style='color:#111;'> 32.42KB </span>","children":null,"spread":false},{"title":"mnist_adv.pdf <span style='color:#111;'> 12.99KB </span>","children":null,"spread":false}],"spread":true},{"title":"Evaluate the model.ipynb <span style='color:#111;'> 16.46KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.48KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.68KB </span>","children":null,"spread":false},{"title":"sopa","children":[{"title":"src","children":[{"title":"solvers","children":[{"title":"euler.py <span style='color:#111;'> 1.63KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 4.64KB </span>","children":null,"spread":false},{"title":"rk_parametric_order2stage2.py <span style='color:#111;'> 3.36KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1B </span>","children":null,"spread":false},{"title":"rk_parametric_order3stage3.py <span style='color:#111;'> 3.69KB </span>","children":null,"spread":false},{"title":"rk_parametric_order4stage4.py <span style='color:#111;'> 7.83KB </span>","children":null,"spread":false},{"title":"rk_parametric.py <span style='color:#111;'> 3.92KB </span>","children":null,"spread":false}],"spread":true},{"title":"models","children":[{"title":"odenet_mnist","children":[{"title":"attacks_runner.py <span style='color:#111;'> 4.12KB </span>","children":null,"spread":false},{"title":"train_validate.py <span style='color:#111;'> 13.83KB </span>","children":null,"spread":false},{"title":"data.py <span style='color:#111;'> 2.69KB </span>","children":null,"spread":false},{"title":"runner_new.py <span style='color:#111;'> 11.64KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 1.57KB </span>","children":null,"spread":false},{"title":"runner.py <span style='color:#111;'> 11.25KB </span>","children":null,"spread":false},{"title":"attacks_utils.py <span style='color:#111;'> 3.42KB </span>","children":null,"spread":false},{"title":"runner_old.py <span style='color:#111;'> 10.52KB </span>","children":null,"spread":false},{"title":"metrics.py <span style='color:#111;'> 1.21KB </span>","children":null,"spread":false},{"title":"layers.py <span style='color:#111;'> 8.88KB </span>","children":null,"spread":false}],"spread":true},{"title":"utils.py <span style='color:#111;'> 1.32KB </span>","children":null,"spread":false},{"title":"odenet_cifar10","children":[{"title":"data.py <span style='color:#111;'> 4.68KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 2.82KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"layers.py <span style='color:#111;'> 20.67KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":".gitignore <span style='color:#111;'> 135B </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