Giter VIP home page Giter VIP logo

hyperandy-gitalks's People

Watchers

 avatar

hyperandy-gitalks's Issues

手写NMS&soft-NMS | HyperAndy

https://wzj.plus/2020/12/18/nms/

手写NMS & soft-NMS1. NMS(非极大抑制)简介非极大抑制算法应用相当广泛,其主要目的是消除多余的框,找到最佳的物体检测位置。 其实现的**主要是将各个框的置信度进行排序,然后选择其中置信度最高的框A,将其作为标准选择其他框,同时设置一个阈值,当其他框B与A的重合程度超过阈值就将B舍弃掉,然后在剩余的框中选择置信度最大的框,重复上述操作。 实现参考faster rcnn源码

faster rcnn相关详解 | HyperAndy

https://wzj.plus/2020/12/28/fasterrcnn/

faster rcnn相关详解1. cascade rcnn1.1 mismatch问题:在R-CNN中用到IoU阈值的有两个地方,分别是Training时Positive与Negative判定,和Inference时计算mAP。 training阶段,RPN网络提出了2000左右的proposals,这些proposals被送入到Fast R-CNN结构中,在Fast R-CNN结构中,首先

看花开花落,淡尽吾生 | HyperAndy

https://wzj.plus/about/

幽窗小记——陈继儒 狐眠败砌,兔走荒台,尽是当年歌舞之地;露冷黄花,烟迷衰草,悉属旧时争战之场。盛衰何常,强弱安在,念此令人心灰。 宠辱不惊,闲看庭前花开花落;去留无意,漫随天外云卷云舒。 晴空朗月,何天不可翱翔,而飞蛾独投夜烛;清泉绿竹,何物不可饮啄,而鸱鸮偏嗜腐鼠。噫!世之不为飞蛾鸱鸮者,几何人哉!

LR推导 | HyperAndy

https://wzj.plus/2020/12/19/lr/

LR推导1. 简介分类任务与回归任务的区别: 输出变量为连续变量的预测问题——回归任务; 输出变量为有限个离散变量的预测问题——分类任务; 逻辑回归的本质是通过回归的方法来解决分类任务,即通过回归预测概率,进而得到分类结果。 2. 相关概念几率:指一件事发生与不发生概率的比值。 对数几率: \begin{equation} logit(p) = log(\frac{p}{1-p}) \end

ROI详解 | HyperAndy

https://wzj.plus/2020/12/28/roi/#post-comment

ROI详解1. ROI pooling在Faster RCNN中用以将rpn生成的候选框region proposal,映射为固定大小的feature map 工作原理为: Conv layers使用的是VGG16,feat_stride=32(即表示,经过网络层后图片缩小为原图的1/32),原图800800,最后一层特征图feature map大小:2525 假定原图中有一region

协同过滤CF详解 | HyperAndy

https://wzj.plus/2020/12/28/cf/

协同过滤CF详解1. user CF(uCF)一般步骤: 构建用户-物品矩阵,将用户表示为物品的向量; 计算向量的相似度;常用相似度为: Jaccard相似系数 \begin{equation} J(A,B) = \frac{A\cap B}{A\cup B} \end{equation} cosine相似系数 \begin{equation} cos\theta = \frac{x_

BN层详解 | HyperAndy

https://wzj.plus/2020/12/28/bn/

BN(batch normalization)详解1. 公式normalization过程 整个过程:batch均值 -> 方差 -> 标准化(正太化)-> 尺度和偏差变换 -> 训练过程更新$\gamma$和$\beta$ 反向传播参数更新的方法: 2. 解决的问题解决问题:解决梯度消失和梯度爆炸问题,同时加快训练。 原理:以sigmoid为激活函数为例 当陷入两端

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.