ImageNet Evolution论文笔记(1)
来源:互联网 发布:网络连接忘记账号密码 编辑:程序博客网 时间:2024/05/29 18:36
Imagenet classification with deep convolutional neural networks
1,The Dataset
ImageNet:we down-sampled the images to a fixed resolution of 256 × 256. Given arectangular image, we first rescaled the image such that the shorter side was of length 256, and then cropped out the central 256×256 patch from the resulting image。subtracting the mean activity over the training set from each pixel
2,The Architecture
five convolutional layers, some of which are followed by max-pooling layers,and three fully-connected layers with a final 1000-way softmax
Local Response Normalization
3,Reducing Overfitting
Data Augmentation
1,extracting random 224 × 224 patches (and their horizontal reflections) from the256×256 images and training our network on these extracted patches;随机地从256x256的原始图像中截取224x224大小的区域(以及水平翻转的镜像),相当于增加了(256-224)^2x2=2048倍的数据量。
2,At test time, the network makes a prediction by extracting five 224 × 224 patches (the four corner patches and the center patch) as well as their horizontal reflections (hence ten patches in all), and averaging the predictions made by the network’s softmax layer on the ten patches。进行预测时,则是取图片的四个角加中间共5个位置,并进行左右翻转,一共获得10张图片,对他们进行预测并对10次结果求均值。
3, perform PCA on the set of RGB pixel values throughout the ImageNet training set.对图像的RGB数据进行PCA处理,并对主成分做一个标准差为0.1的高斯扰动,增加一些噪声。
Dropou
1,At test time, we use all the neurons but multiply their outputs by 0.5
,2,use dropout in the first two fully-connected layers
4,Details of learning
1,a batch size of 128 examples, momentum of 0.9, and weight decay of 0.0005
2,We initialized the weights in each layer from a zero-mean Gaussian distribution with standard deviation 0.01. We initialized the neuron biases in the second, fourth, and fifth convolutional layers,as well as in the fully-connected hidden layers, with the constant 1. This initialization accelerates the early stages of learning by providing the ReLUs with positive inputs. We initialized the neuron biases in the remaining layers with the constant 0.
结构代码:
- ImageNet Evolution论文笔记(1)
- ImageNet Evolution论文笔记(2)
- ImageNet Evolution论文笔记(3)
- ImageNet Evolution论文笔记(4)
- ImageNet Classification with Deep Convolutional Neural Networks论文笔记
- 论文笔记《ImageNet Classification with Deep Convolutional Neural Networks》
- 论文笔记ImageNet Classification with Deep Convolutional Neural Networks(AlexNet)
- 论文笔记:ImageNet classification with deep convolution neural networks
- ImageNet Classification with Deep Convolutional Neural Networks 论文笔记
- 论文笔记:ImageNet Classification with Deep Convolutional Neural Networks
- 论文阅读(1)——ImageNet Classification with Deep Convolutional Neural Networks
- Imagenet 论文里的 single crop evaluation(test)
- caffe学习笔记(三)ImageNet实例
- Deep learning论文笔记一:ImageNet Classification with Deep Convolutional Neural Networks
- 经典计算机视觉论文笔记——《ImageNet Classification with Deep Convolutional Neural Networks》
- [深度学习论文笔记][Image Classification] ImageNet Classification with Deep Convolutional Neural Networks
- RCNN论文笔记(1)
- 【深度学习经典论文翻译1】AlexNet-ImageNet Classification with Deep Convolutional Neural Networks全文翻译
- 水经注地图发布服务中间件服务配置功能说明
- 安友高架桥绿化轻质蓄水种植容器AY-80
- 对象结构型模式——外观模式(Pacade Pattern)
- map集合题
- 秒懂JS对象、构造器函数和原型对象之间的关系
- ImageNet Evolution论文笔记(1)
- ansible 配置变量
- 16秋计算机JAVA第二次课作业(钟永钜)
- 基于Spring Boot和Spring Cloud实现微服务架构学习
- ubuntu14.04安装MRPT
- JS匹配字符串中电话号码,并且隐藏字符串中的电话号
- Mysql使用心得(2)
- 11
- 大道至简,职场上做人做事做管理