Skip to content

Commit 6ea485b

Browse files
committed
Add chapter 4 figures
1 parent a59ab1c commit 6ea485b

28 files changed

+38
-6
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ We delve into the world of image classification in a mere five lines of Keras co
4444

4545
We use transfer learning to reuse a previously trained network on a new custom classification task to get near state-of-the-art accuracy in a matter of minutes. We then slice and dice the results to understand how well is it classifying. Along the way, we build a common machine learning pipeline, which is repurposed throughout the book. Bonus: we hear from **Jeremy Howard**, co-founder of fast.ai, on how hundreds of thousands of students use transfer learning to jumpstart their AI journey.
4646

47-
[**Chapter 4 - Building a Reverse Image Search Engine: Understanding Embeddings**](https://github.com/practicaldl/Practical-Deep-Learning-Book/tree/master/code/chapter-4) | [Read online](https://learning.oreilly.com/library/view/practical-deep-learning/9781492034858/ch04.html)
47+
[**Chapter 4 - Building a Reverse Image Search Engine: Understanding Embeddings**](https://github.com/practicaldl/Practical-Deep-Learning-Book/tree/master/code/chapter-4) | [Read online](https://learning.oreilly.com/library/view/practical-deep-learning/9781492034858/ch04.html) | [Figures](figures/chapter-4)
4848

4949
Like Google Reverse Image Search, we explore how one can use embeddings—a contextual representation of an image to find similar images in under ten lines. And then the fun starts when we explore different strategies and algorithms to speed this up at scale, from thousands to several million images, and making them searchable in microseconds.
5050

figures/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ This directory contains references to the figures used within the book. All imag
1111
| [Chapter 1 - Exploring the Landscape of Artificial Intelligence](chapter-1/) |
1212
| [Chapter 2 - What’s in the Picture: Image Classification with Keras](chapter-2/) |
1313
| [Chapter 3 - Cats versus Dogs: Transfer Learning in 30 Lines with Keras](chapter-3/) |
14-
| Chapter 4 - Building a Reverse Image Search Engine: Understanding Embeddings |
14+
| [Chapter 4 - Building a Reverse Image Search Engine: Understanding Embeddings](chapter-4/) |
1515
| Chapter 5 - From Novice to Master Predictor: Maximizing Convolutional Neural Network Accuracy |
1616
| Chapter 6 - Maximizing Speed and Performance of TensorFlow: A Handy Checklist |
1717
| Chapter 7 - Practical Tools, Tips, and Tricks |

figures/chapter-1/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Chapter 1: Exploring the Landscape of Artificial Intelligence
1+
# Chapter 1 - Exploring the Landscape of Artificial Intelligence
22

33
Note: All images in this directory, unless specified otherwise, are licensed under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode).
44

figures/chapter-2/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Chapter 2: What's in the Picture: Image Classification with Keras
1+
# Chapter 2 - What's in the Picture: Image Classification with Keras
22

33
Note: All images in this directory, unless specified otherwise, are licensed under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode).
44

figures/chapter-3/README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Chapter 3: Cats Versus Dogs: Transfer Learning in 30 Lines with Keras
1+
# Chapter 3 - Cats Versus Dogs: Transfer Learning in 30 Lines with Keras
22

33
Note: All images in this directory, unless specified otherwise, are licensed under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode).
44

@@ -13,7 +13,7 @@ Note: All images in this directory, unless specified otherwise, are licensed und
1313
| [3-5](5-finetuning.png?raw=true) | Fine tuning a convolutional neural network | |
1414
| [3-6](6-folder-tree-structure.png?raw=true) | Example directory structure of the training and validation data for different classes | |
1515
| [3-7](7-overfitting-underfitting.png?raw=true) | Underfitting, overfitting, and ideal fitting for points close to a sine curve | |
16-
| [3-8](8-rabbit-augmentations.png?raw=true) | Possible image augmentations generated from a single image | |
16+
| [3-8](8-rabbit-augmentations.jpg?raw=true) | Possible image augmentations generated from a single image | |
1717
| [3-9](9-highest-probability-dogs.png?raw=true) | Images with the highest probability of containing dogs | |
1818
| [3-10](10-lowest-probability-dogs.png?raw=true) | Images with the lowest probability of containing dogs | |
1919
| [3-11](11-cats-highest-probability-containing-dogs.png?raw=true) | Images of cats with the highest probability of containing dogs | |

figures/chapter-4/1-rgb-histogram.png

1.22 MB
Loading

figures/chapter-4/10-tsne-grid.png

3.91 MB
Loading
Loading
Loading
Loading

0 commit comments

Comments
 (0)