Coursera 笔记

DeepLearning.AI

Convolutional Neural Networks

卷积神经网络

46 notes · 103 images · 39/70 条官方条目有笔记 · certified

Coursera ↗

Module 01

Foundations of Convolutional Neural Networks

9 / 19 篇
  1. 01Computer Vision计算机视觉
  2. 02Edge Detection Example边缘检测示例
  3. 03More Edge Detection边缘检测进阶
  4. 04Padding填充
  5. 05Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!
  6. 06Strided Convolutions步长卷积
  7. 07Convolutions Over Volume三维卷积
  8. 08One Layer of a Convolutional Network单层卷积网络
  9. 09Clarifications about Upcoming Simple Convolutional Network Example Video
  10. 10Simple Convolutional Network Example简单卷积网络示例
  11. 11Pooling Layers
  12. 12Clarifications about Upcoming CNN Example Video
  13. 13CNN Example
  14. 14Clarifications about Upcoming Why Convolutions?
  15. 15Why Convolutions?
  16. 16Lecture Notes W1
  17. 17Graded Assignment: The Basics of ConvNets评分作业：卷积网络基础
  18. 18(Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspace
  19. 19Yann LeCun Interview
Module 02

Deep Convolutional Models: Case Studies

9 / 21 篇
  1. 01Why look at case studies?
  2. 02Classic NetworksLeNet-5、AlexNet 和 VGGNet
  3. 03ResNets残差网络
  4. 04ResNets理解残差网络（ResNet）
  5. 05Why ResNets Work?残差网络为何有效
  6. 06Networks in Networks and 1x1 Convolutions
  7. 07Clarifications about Upcoming Inception Network Motivation Video
  8. 08Inception Network Motivation
  9. 09Inception NetworkInception 网络
  10. 10MobileNet
  11. 11MobileNet Architecture
  12. 12EfficientNet
  13. 13Using Open-Source Implementation
  14. 14Transfer Learning
  15. 15Data Augmentation
  16. 16State of Computer Vision计算机视觉现状
  17. 17Lecture Notes W2
  18. 18Graded Assignment: Deep Convolutional Models评分作业：深度卷积模型
  19. 19Note on the Upcoming Programming Assignment - Residual Networks
  20. 20Residual Networks残差网络（编程作业）
  21. 21Transfer Learning with MobileNet基于 MobileNet 的迁移学习
Module 03

Object Detection

15 / 19 篇
  1. 01Object Localization目标定位
  2. 02Landmark Detection关键点检测
  3. 03Object Detection目标检测
  4. 04Clarifications about Upcoming Convolutional Implementation of Sliding Windows Video
  5. 05Convolutional Implementation of Sliding Windows滑动窗口的卷积实现
  6. 06Bounding Box Predictions边界框预测
  7. 07Intersection Over Union交并比
  8. 08Non-max Suppression非极大值抑制
  9. 09Anchor Boxes锚框
  10. 10Clarifications about Upcoming YOLO Algorithm Video
  11. 11YOLO AlgorithmYOLO 算法
  12. 12Region Proposals (Optional)区域提议（可选）
  13. 13Semantic Segmentation with U-Net基于 U-Net 的语义分割
  14. 14Transpose Convolutions转置卷积
  15. 15U-Net Architecture IntuitionU-Net 架构直观理解
  16. 16U-Net ArchitectureU-Net 架构
  17. 17Lecture Notes W3
  18. 18Graded Assignment: Detection Algorithms评分作业：检测算法
  19. 19Clear Output Before Submitting (For U-Net Assignment)
Module 04

Special Applications: Face recognition & Neural Style Transfer

13 / 18 篇
  1. 01What is Face Recognition?什么是面部识别
  2. 02One Shot Learning一次学习
  3. 03Siamese Network孪生网络
  4. 04Triplet Loss三元组损失
  5. 05Clarifications about Upcoming Face Verification and Binary Classification Video
  6. 06Face Verification and Binary Classification面部验证与二分类
  7. 07What is Neural Style Transfer?什么是神经风格迁移
  8. 08What are deep ConvNets learning?深度卷积网络在学什么
  9. 09Cost Function代价函数
  10. 10Content Cost Function内容代价函数
  11. 11Clarifications about Upcoming Style Cost Function Video
  12. 12Style Cost Function风格代价函数
  13. 131D and 3D Generalizations一维与三维推广
  14. 14Lecture Notes W4
  15. 15Graded Assignment: Special Applications - Face Recognition & Neural Style Transfer评分作业：特殊应用——面部识别与神经风格迁移
  16. 16[IMPORTANT] Reminder about end of access to Lab Notebooks
  17. 17References参考文献
  18. 18Acknowledgments