coursera deep learning course4 week2
来源:互联网 发布:长沙网络推广外包 编辑:程序博客网 时间:2024/05/18 20:51
ResNets
The identity block
The convolutional block ( You can use this type of block when the input and output dimensions don’t match up. The CONV2D layer in the shortcut path is used to resize the input xx to a different dimension, so that the dimensions match up in the final addition needed to add the shortcut value back to the main path. (This plays a similar role as the matrix WsWs discussed in lecture.) For example, to reduce the activation dimensions’s height and width by a factor of 2, you can use a 1x1 convolution with a stride of 2. The CONV2D layer on the shortcut path does not use any non-linear activation function. Its main role is to just apply a (learned) linear function that reduces the dimension of the input, so that the dimensions match up for the later addition step. )
1X1 conv&inception network motivation
让各种规模的卷积核和池化层处理完的volume叠加在一起。
用1X1 CONV可以减少计算量
transfer learning
和前面讲的差不多如果数据很少,可以只替换最后的层。数据量多可以将前面的也进行训练。框架中有冻结前面层参数的设置。Data augmentation
1). mirroring
2). random cropping
3). rotation
4). shearing
5). local warping
6). color shifting
7). PCAData vs. hand-engineering
Two sources of knowledge从这两方面可以提高模型的效果,越是数据少的领域越需要手动设计,例如特征、结构、算法等。
- coursera deep learning course4 week2
- coursera deep learning course4 week3
- coursera deep learning course3 week2
- COURSERA Machine Learning WEEK1&&WEEK2
- coursera Machine Learning Week2 学习笔记
- Coursera Machine Learning Week2 学习笔记
- 【Coursera Machine Learning】 Week2 学习笔记
- coursera deep learning course2 week3
- coursera deep learning course3 week1
- deep learning(coursera) week1 Introduction to deep learning
- Andrew Ng(吴恩达) deep learning 课程 (coursera)
- 笔记 | 吴恩达Coursera Deep Learning学习笔记
- 笔记 | 吴恩达Coursera Deep Learning学习笔记
- Coursera-Crypto1 Week2
- coursera week2题目
- Coursera-Deep Learning Specialization 课程之(一):Neural Networks and Deep Learning-weak1
- Coursera-Deep Learning Specialization 课程之(一):Neural Networks and Deep Learning-weak2
- Coursera-Deep Learning Specialization 课程之(一):Neural Networks and Deep Learning-weak2编程作业
- BITMAPFILEHEADER、BITMAPINFOHEADER及BMP结构详解
- 搜索添加数据库+清空历史记录
- 双机热备系统的方案与软件浅析
- Matlab读取文件函数总结
- 数据结构第七周项目-停车场模拟(栈和队列综合)
- coursera deep learning course4 week2
- linux基本命令
- 【模9】digital roots[hdu 1013]
- .net中mvc问卷制作
- SVN迁移到GIT后续推送
- angular路由
- 当程序员没了互联网,该如何继续学习写代码?
- 大一新生信息可视化展示(基于Echarts)
- Spring教程第四篇:Spring事务