自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+
  • 博客(6)
  • 资源 (5)
  • 问答 (1)
  • 收藏
  • 关注

原创 openai docker 自定义基础容器 服务器配置

基本模式是这样子的.我们需要将服务器上现成的image pull到本地, 按照自己的实验环境进行配置,保存为新的image, 然后再push到服务器上.假设服务器IP为72.13.0.0首先设置安全仓库为服务器Ipvim /etc/docker/daemon.json# 修改内容如下{"insecure-registries":["172.13.0.0"]}# 重启docker 使得配置...

2020-07-31 18:29:17 665

原创 docker入门课程

Docker 架构Ubuntu Docker 安装使用官方安装脚本自动安装手动安装Docker 镜像加速Docker Hello World运行交互式的容器启动容器(后台模式)停止容器Docker 容器使用获取镜像启动容器启动已停止运行的容器后台运行停止一个容器进入容器导出和导入容器删除容器Docker 镜像使用列出镜像列表获取一个新的镜像查找镜像删除镜像创建镜像更新镜像**构建镜像**设置镜像标签Docker 容器连接Docker 架构Docker 包括三个基本概念:镜像(Image):Dock.

2020-07-30 14:25:04 265

原创 【DKNN】Distilling the Knowledge in a Neural Network 第一次提出神经网络的知识蒸馏概念

Distilling the Knowledge in a Neural NetworkAbstract1 Introduction2 Distillation2.1 Matching logits is a special case of distillation3 Preliminary experiments on MNIST4 Experiments on speech recognition4.1 Results5 Training ensembles of specialists on ver.

2020-07-23 11:02:22 906

原创 【DML】Deep Mutual Learning 深度相互学习,神经网络也可以协作

Deep Mutual LearningAbstract1. Introduction2. Related WorkModel DistillationCollaborative Learning3. Deep Mutual Learning3.1. Formulation3.2. Optimisation3.3. Extension to Larger Student Cohorts3.4. Extension to Semi-supervised Learning5. Conclusion论文:h.

2020-07-22 20:09:30 2583

原创 【MMT】ICLR 2020: MMT(Mutual Mean-Teaching)方法,无监督域适应在Person Re-ID上性能再创新高

为了减轻噪音伪标签的影响,文章提出了一种无监督的MMT(Mutual Mean-Teaching)方法,通过在迭代训练的方式中使用离线精炼硬伪标签和在线精炼软伪标签,来学习更佳的目标域中的特征。同时,还提出了可以让Traplet loss支持软标签的soft softmax-triplet loss”。 该方法在域自适应任务方面明显优于所有现有的Person re-ID方法,改进幅度高达18.2%。MUTUAL MEAN-TEACHING: PSEUDO LABEL REFINERY FOR UNSUP.

2020-07-07 19:58:11 1578

原创 【FSR】Feature Space Regularization for Person Re-Identification with One Sample

Feature Space Regularization for Person Re-Identification with One SampleAbstractI. INTRODUCTIONFramework.Our Method.II. RELATED WORKSA. Supervised Re-IDB. Semi-supervised Re-IDC. Unsupervised re-IDD. Progressive LearningIII. THE PROPOSED METHODA. Overall.

2020-07-05 17:36:15 535 4

MPI and neural Rendering

MPI and neural Rendering

2022-09-05

神经隐式SLAM方法presentation

神经隐式SLAM方法presentation

2022-09-05

HDR-NeRF-presentation

HDR-NeRF-presentation

2022-09-05

《百面深度学习》之元学习.pdf

百面深度学习 之 元学习知识笔记

2021-06-22

Simple_Rules_AI.pdf

Can artificial intelligence, in particular, machine learning algorithms, replace the idea of simple rules, such as first possession and voluntary exchange in free markets, as a foundation for public policy? This paper argues that the preponderance of the evidence sides with the interpretation that while artificial intelligence will help public policy along important aspects, simple rules will remain the fundamental guideline for the design of institutions and legal environments where markets operate. “Digital socialism” might be a hipster thing to talk about in Williamsburg or Shoreditch, but it is as much of a chimera as “analog socialism.”

2020-05-27

Hands-onPythonTutorial.pdf

You have probably used computers to do all sorts of useful and interesting things. In each application, the computer responds in different ways to your input, from the keyboard, mouse or a file. Still the underlying operations are determined by the design of the program you are given. In this set of tutorials you will learn to write your own computer programs, so you can give the computer instructions to react in the way you want.

2020-05-27

工程领域大数据和人工智能原则.pdf

工程领域大数据和人工智能原则。近年来,大数据和人工智能技术快速发展,其应用广泛落地,已经为 我们的生产和生活带来显著的贡献,在辅助个人能力提升,改善人民生活 品质,促进经济和社会发展,应对全球重大挑战(如:气候变化,粮食短 缺等)及促进落实联合国可持续发展目标等方面带来巨大机遇。特别是在 工程领域,作为第四次工业革命的主要驱动力之一,大数据和人工智能正 在推动研发、规划、设计、制造、测试、操作和维护等方面的革新,并可 提高生产力及工程项目的质量、安全和效率,同时减少碳排放,降低物耗、 能耗和成本。此外,它们还有助于打击腐败、维护工程操守。

2020-05-27

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除