At present,The latest verion of offical OpenCV is 4.5.2。 In this blog, I introduce how to compile OpenCV from source code and enable GPU/CUDA support - GPU: Tesla V100 - CUDA: 11.0 - CUDA Capability: 7.0 (corresponding to GPU Tesla V100) - OS: Ubuntu 20.04 # I…

2021年2月25日 0条评论 4644点热度 0人点赞 Dong Wang 阅读全文

对于一个全新的Ubuntu20.04系统,我们将使用这个脚本安装GPU驱动、CUDA11.0、cudnn11.2、Python、Pytorch和Opencv。 注意,请首先手动下载cudnn11.2 地址:https://developer.nvidia.com/rdp/cudnn-download 注意,请首先手动下载cudnn11.2 地址:https://developer.nvidia.com/rdp/cudnn-download 注意,请首先手动下载cudnn11.2 地址:https://develop…

2021年1月29日 1条评论 2538点热度 0人点赞 Dong Wang 阅读全文

这篇文章介绍了我近期的工作,一个端到端的手势识别模型。 Introduction 识别手势在智能交互系统领域是一个基本研究课题。能够快速识别出用户的手势并做出反应对智能交互系统的用户体验有很重要的作用。手势识别在安全、K12教育、工业领域都有广泛的应用。 本文介绍一个端到端的手势识别系统的模型。这个模型的输入是一张240*320 的 RGB 图像,输出是6种预定手势的概率。我们取概率最大者为预测的手势类型。 我们定义如下的6种手势: Data 模型的输入数据是由60个经过标注的视频数据采样而来。一共有10个人,每个…

2020年5月26日 0条评论 3521点热度 1人点赞 Dong Wang 阅读全文

Natural Computation Methods for Machine Learning Note 15 In this article, we talk about Particle Swarm Optimization. In last post, we talked Computational tools, including Cellular automata Ant Colony Optimization Particle Swarm Optimization Particle Swarm Opt…

2020年3月28日 0条评论 2855点热度 1人点赞 Dong Wang 阅读全文

Natural Computation Methods for Machine Learning Note 14 Swarm Intelligence Intelligence <- Social behavior Intelligence can emerge from social interaction. Emergent behaviour – when a group behaves in ways that were not ”programmed” into its members Swarm …

2020年3月25日 0条评论 3067点热度 0人点赞 Dong Wang 阅读全文

Natural Computation Methods for Machine Learning Note 13 Properties of EC EC is parallel search (many balls in the landscape). Want to prevent all individuals from converging to the same solution (premature convergence – a common problem) The task of mutation …

2020年3月20日 0条评论 2007点热度 0人点赞 Dong Wang 阅读全文

Natural Computation Methods for Machine Learning Note 12 From course, I learned Evolutional Computing. Evolutionary computing (EC) population method Used for problems where the task is to maximize some measure of success Same family of problems as in RL, but v…

2020年3月20日 0条评论 1815点热度 0人点赞 Dong Wang 阅读全文

Natural Computation Methods for Machine Learning Note 11 Let us firstly revisit completive learning and SOFM Review CL and SOFM A node position (in the input space) is its weight vector, i.e. nodes move around in the same space as the data. Purpose of unsuperv…

2020年3月4日 0条评论 2083点热度 0人点赞 Dong Wang 阅读全文

Natural Computation Methods for Machine Learning Note 10 In this note, we are going talk about Deep Learning very briefly. Radial Basis Function Networks RBFNs are feedforward networks, where: The hidden nodes (the RBF nodes) compute distances, instead of weig…

2020年3月2日 0条评论 2022点热度 0人点赞 Dong Wang 阅读全文

Unsupervised Learning To learn from unlabeled data (only inputs, no target information). Most often for classification. Requires that class membership can be detected by structural properties (features) in the data, and that the learning system can be fund the…

2020年3月2日 0条评论 1991点热度 0人点赞 Dong Wang 阅读全文