pre-training generative networks training
Nginx config generator All In One
Nginx config generator All In One
NGINXConfig, Nginx 配置配置高性能、安全、稳定的 Nginx 服务器的最简单方法
......
AtCoder Regular Contest 123 E Training
洛谷传送门 AtCoder 传送门 不妨假设 $B_X \le B_Y$。设 $f(x) = A_X + \frac{x}{B_X}, g(x) = A_Y + \frac{x}{B_Y}, F(x) = \left\lfloor{f(x)}\right\rfloor, G(x) = \left\l ......
EXPLORING MODEL-BASED PLANNING WITH POLICY NETWORKS
**发表时间：**2020（ICLR 2020） **文章要点：**这篇文章说现在的planning方法都是在动作空间里randomly generated，这样很不高效（其实瞎扯了，很多不是随机的方法啊）。作者提出在model based RL里用policy网络来做online planning ......
Cluster-GCN An Efficient Algorithm for Training Deep Convolution Networks
Chiang W., Liu X., Si S., Li Y., Bengio S. and Hsieh C. Cluster-GCN: An efficient algorithm for training deep and large graph convolutional networks. ......
Representation Learning for Attributed Multiplex Heterogeneous Network
Cen Y., Zou X., Zhang J., Yang H., Zhou J. and Tang J. Representation learning for attributed multiplex heterogeneous network. KDD, 2019. 概 本文在 Attrib ......
服务器断电后启动失败报错：Generating /run/initramfs/rdsosreport.txt
一、现象 服务器断电，然后启动时发现起不来，连接显示器发现报错，如下所示： 原因：一般是服务器突然断电导致文件损坏所致，只要修复回去就好 二、解决过程 2.1 寻找/dev/ *-root 文件 说明： /dev/mapper 目录下一般有三个文件，其中 centos-root 是我们需要修复的。有 ......
This dataset does not have valid histogram required for classification method, run Calculate Statistics tool to generate histogram.
此数据集没有分类方法所需的有效直方图，请运行“计算统计信息”工具生成直方图。 参考1：https://blog.csdn.net/soderayer/article/details/125409022 参考2：https://blog.csdn.net/aGang_Gg/article/detail ......
Cycle GAN：Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
paper：https://arxiv.org/pdf/1703.10593.pdf [2017] code 参考： https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix https://zhuanlan.zhihu.com/p/792211 ......
Spatiotemporal Remote Sensing Image Fusion Using Multiscale Two-Stream Convolutional Neural Networks
Spatiotemporal Remote Sensing Image Fusion Using Multiscale Two-Stream Convolutional Neural Networks abstract 地表反射率图像的渐变和突变是现有STF方法的主要挑战。(Gradual and ......
一种新的流：为 Java 加入生成器(Generator)特性
这篇文章不是工具推荐，也不是应用案例分享。其主题思想，是介绍一种全新的设计模式。它既拥有抽象的数学美感，仅仅从一个简单接口出发，就能推演出庞大的特性集合，引出许多全新概念。同时也有扎实的工程实用价值，由其实现的工具，性能均可显著超过同类的头部开源产品。 ......
ubuntu - k3s安装失败出现unable to find suitable network address.error
系统时ubuntu18 原因： 离线安装k3s 需要手动设定 ip的 网关 使用ip route 查看是否出现default via xxxx.xxxx.x.x dev ens33 xxxxx 内容。 如果没有出现 说明没有默认网关。 方式1 ： 临时生效 使用命令： ip route add de ......
Invariant and Equivariant Graph Networks
Maron H., Ben-Hamu H., Shamir N. and Lipman Y. Invariant and equivariant graph networks. ICLR, 2019. 概 有些时候, 我们希望网络具有: 不变性 (Invariant): $$ f(PX) = f(X ......
【IP】Block Memory Generator IP核
简单介绍一种利用Block Memory Generator IP核生成ROM，实现查找表功能的例子 一、BasicInterface Type：NativeMemory Type：single port ROM 二、Port A Optionsenable port type:always ena ......
Vulnhub之 BoredHackerBlog: Social Network 2.0靶机详细测试过程
Socnet 作者：jason huawen 靶机信息 名称：BoredHackerBlog: Social Network 2.0 地址： https://www.vulnhub.com/entry/boredhackerblog-social-network-20,455/ 识别目标主机IP地址 ......
kubenetes pod networ flannel network
kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml https://github.com/flannel-io/flannel/blob/mas ......
Unlock the Power of High-Performance Networking with the IPQ9554
Unlock the Power of High-Performance Networking with the IPQ9554 In today's world, reliable and high-speed internet connectivity is essential for ever ......
Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA
一、项目背景 We introduce Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. Preliminary ......
论文解读（VAT）《Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning》
论文信息 论文标题：Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning论文作者：Takeru Miyato, S. Maeda, Masanori Koya ......
论文解读《Do We Need Zero Training Loss After Achieving Zero Training Error?》
论文信息 论文标题：Do We Need Zero Training Loss After Achieving Zero Training Error?论文作者：Takashi Ishida, I. Yamane, Tomoya Sakai, Gang Niu, M. Sugiyama论文来源：20 ......
教我怎么用docker的network
Docker 提供了一种为容器创建和管理网络以相互通信的方法。 创建 Docker 网络有多种方法，最简单的方法是使用 docker network create 命令。 此命令创建一个具有指定名称和驱动程序的新网络。 驱动程序指定网络上的容器如何相互通信。 最常见的驱动程序是桥接驱动程序，它用于为 ......
猛读论文13 |【CVPR 2022 UDA】Unleashing Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
动机 解决（1）对比学习管道中的增强通常会扭曲人物图像中的判别线索（2）细粒度的局部特征人物图像尚未得到充分探索。 思路 方法 ......
猛读论文6 |【CVPR 2022】Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification
用于孤立摄像机监督行人重识别的摄像机条件稳定特征生成 动机 常规ReID，对于一个ID，在不同摄像头拍摄的图片上提取跨相机视图不变特征 而 ISCS情况下，无法做到同一个ID采集到不同摄像头图片 由于跨相机样本在人体 Re-ID 模型训练中起着重要作用，而在 ISCS 设置下不存在此类配对图像，因此 ......
mysql generate 1000000 rows with random data
CREATE TABLE `data` ( `id` bigint(20) NOT NULL AUTO_INCREMENT, `datetime` timestamp NULL DEFAULT CURRENT_TIMESTAMP, `channel` int(11) DEFAULT NULL, `v ......
CentOS网卡无法启动返回'Failed to start LSB：Bring up/down networking.'
装了一台虚机，配置docker服务的时候发现忘了开CPU虚拟化，关机开启后再登录，发现网卡down了，重启网卡报错。 1. journalctl -ex #查看日志，发现返回错误'Failed to start LSB：Bring up/down networking.'； 2. vi /var/l ......
迁移学习（PAT）《Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation》
论文信息 论文标题：Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation论文作者：Weili Shi, Ronghang Zhu, Sheng Li论文来源：KDD 2022论文地址：dow ......
Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
Zou D., Hu Z., Wang Y., Jiang S., Sun Y. and Gu Q. Layer-dependent importance sampling for training deep and large graph convolutional networks. NIPS, ......
1094 The Largest Generation
A family hierarchy is usually presented by a pedigree tree where all the nodes on the same level belong to the same generation. Your task is to find t ......
Unlock the Power of High-Performance Networking with the IPQ9554
In today's world, reliable and high-speed internet connectivity is essential for everything from online gaming and streaming to remote work and learni ......
Heterogeneous Graph Attention Network
Wang X., Ji H., Shi C., Wang B., Cui P., Yu P. and Ye Y. Heterogeneous graph attention network. WWW, 2019. 概 Attention + 异构图. 符号说明 $\mathcal{G} = (\ma ......