老是忘，记一下吧创建 git 仓库:mkdir xxx cd xxx git init touch README.md git add README.md git commit -m "first commit" git remote add origin https://gitee.com/fmujie/xxxx.git git push -u origin "master"已有仓库，只需与远程建立连接cd existing_git_repo git remote add origin https://gitee.com/fmujie/xxx.git git push -u origin "master"以下参考自：Git本地创建分支并推送到远程 - 简书 (jianshu.com)1. 创建本地...

R-Drop: Regularized Dropout for Neural NetworksDropout is a powerful and widely used technique to regularize the training of deep neural networks. Dropout在训练和推理时存在不一致的问题（集成学习）R 对每个子模型的分布做一个KL散度import numpy as np def train_r_drop(ratio, x, w1, b1, w2, b2): # 输入复制一份 x = torch.cat([x, x], dim=0) layer1 = np.maximum(0, np.dot(w1, x) + b1) mask1 = np.random.binomial(1, 1...

安装部署说明书参照白俊遥博客https://baijunyao.com，跟着教程过了一遍后端接口环境搭建应用于生产环境的的服务器为不带桌面的版本 Linux 系统，使用国产的免费的面板宝塔来方便搭建LNMP环境；要使用宝塔面板首先需要开启端口；腾讯云：https://www.bt.cn/bbs/thread-1229-1-1.html阿里云：https://www.bt.cn/bbs/thread-2897-1-1.html华为云：https://www.bt.cn/bbs/thread-3923-1-1.html然后执行下面的命令即可；yum install -y wget && wget -O install.sh http://download.bt.cn/install/install.sh && sh install....

home\.cache\torch\checkpoints有什么用，遇到就知道了，有时候集群网不好，可以本地下载后传到集群上的指定目录，就不用在集群上龟速下载了。

NN.DROPOUTCLASStorch.nn.Dropout(p=0.5, inplace=False)Parametersp (float) – probability of an element to be zeroed. Default: 0.5inplace (bool) – If set to True, will do this operation in-place. Default: FalseShape:Input: (∗)(∗). Input can be of any shapeOutput: (∗)(∗). Output is of the same shape as inputm = nn.Dropout(p=0.2) input = torch.randn(20, 16) output = m(input)如何判断当前是否为Trai...