smoothing-consistency:论文代码“对平滑分类器的稳健性进行一致性正则化”（NeurIPS 2020）

【文件属性】：
文件名称：smoothing-consistency:论文代码“对平滑分类器的稳健性进行一致性正则化”（NeurIPS 2020）
文件大小：9.74MB
文件格式：ZIP
更新时间：2021-05-29 01:24:14
deep-learning robustness adversarial-machine-learning adversarial-defense randomized-smoothing 平滑分类器认证稳健性的一致性正则化 (NeurIPS2020) 该存储库包含和的论文“平滑分类器的证明稳健性的一致性正则化”代码。 依存关系 conda create -n smoothing-consistency python=3 conda activate smoothing-consistency # IMPORTANT: Please make sure `pytorch != 1.4.0` # Currently, our code is not compatible to `pytorch == 1.4.0`; # See more details at `https://github.com/pytorch/pytorch/issues/32395`. # Below is for linux, with CUDA 10; see https://pytorc