Add chapter 3 figures (#111)

* Fix image path

* Add chapter 3 figures

Author: meherkasam

README.md

@@ -40,7 +40,7 @@ We take a tour of this evolving landscape, from 1950s till today, and analyze th
 
 We delve into the world of image classification in a mere five lines of Keras code. We then learn what neural networks are paying attention to while making predictions by overlaying heatmaps on videos. Bonus: we hear the motivating personal journey of **François Chollet**, the creator of Keras, illustrating the impact a single individual can have.
 
-[**Chapter 3 - Cats versus Dogs: Transfer Learning in 30 Lines with Keras**](https://github.com/practicaldl/Practical-Deep-Learning-Book/tree/master/code/chapter-3) | [Read online](https://learning.oreilly.com/library/view/practical-deep-learning/9781492034858/ch03.html)
+[**Chapter 3 - Cats versus Dogs: Transfer Learning in 30 Lines with Keras**](https://github.com/practicaldl/Practical-Deep-Learning-Book/tree/master/code/chapter-3) | [Read online](https://learning.oreilly.com/library/view/practical-deep-learning/9781492034858/ch03.html) | [Figures](figures/chapter-3)
 
 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.
 

figures/README.md

@@ -10,7 +10,7 @@ This directory contains references to the figures used within the book. All imag
 |:---|
 | [Chapter 1 - Exploring the Landscape of Artificial Intelligence](chapter-1/) |
 | [Chapter 2 - What’s in the Picture: Image Classification with Keras](chapter-2/) |
-| Chapter 3 - Cats versus Dogs: Transfer Learning in 30 Lines with Keras |
+| [Chapter 3 - Cats versus Dogs: Transfer Learning in 30 Lines with Keras](chapter-3/) |
 | Chapter 4 - Building a Reverse Image Search Engine: Understanding Embeddings |
 | Chapter 5 - From Novice to Master Predictor: Maximizing Convolutional Neural Network Accuracy |
 | Chapter 6 - Maximizing Speed and Performance of TensorFlow: A Handy Checklist |

figures/chapter-1/README.md

@@ -5,11 +5,11 @@ Note: All images in this directory, unless specified otherwise, are licensed und
 ## Figure List
 
 | Figure number | Description | Notes |
-|:---|:-----|:---|
+|:---|:---|:---|
 | [1-1](1-may-carson.png?raw=true) | Dr. May Carson | |
 | [1-2](2-ai-terminology.png?raw=true) | The relationship between AI, machine learning, and deep learning | |
 | [1-3](3-perceptron.png?raw=true) | An example of a perceptron | |
-| [1-4](4-neural-network.png?raw=true) | An example multilayer neural network | Built using [NN-SVG](http://alexlenail.me/NN-SVG/) | |
+| [1-4](4-neural-network.png?raw=true) | An example multilayer neural network | Built using [NN-SVG](http://alexlenail.me/NN-SVG/) |
 | [1-5](http://www.cs.cmu.edu/Groups/ahs/navlab_list.html) | The autonomous NavLab 1 from 1986 in all its glory | |
 | [1-6](6-mnist.png?raw=true) | A sample of handwritten digits from the MNIST dataset | |
 | [1-7](7-imagenet-accuracy.png?raw=true) | Evolution of winning entries at ImageNet LSVRC | |

figures/chapter-2/README.md

@@ -5,10 +5,10 @@ Note: All images in this directory, unless specified otherwise, are licensed und
 ## Figure List
 
 | Figure number | Description |
-|:---|:-----|
+|:---|:---|
 | [2-1](1-cat-visualization.png?raw=true) | Plot showing the contents of the input file cat.jpg |
 | [2-2](2-dog-visualization.png?raw=true) | Plot showing the contents of the input file dog.jpg |
 | [2-3](3-colab-play.png?raw=true) | Running the notebook on Google Colab using the browser |
 | [2-4](http://image-net.org/explore) | The categories and subcategories in the ImageNet dataset |
 | [2-5](5-imagenet-treemap.png?raw=true) | Treemap of ImageNet and its classes |
-| [2-6](6-dog-output.png?raw=true) | Original image of a dog and its generated heatmap |
+| [2-6](6-dog-output.jpg?raw=true) | Original image of a dog and its generated heatmap |

figures/chapter-3/1-transfer-learning-piano.png

@@ -0,0 +1,24 @@
+# Chapter 3: Cats Versus Dogs: Transfer Learning in 30 Lines with Keras
+
+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).
+
+## Figure List
+
+| Figure number | Description | Notes |
+|:---|:---|:---|
+| [3-1](1-transfer-learning-piano.png?raw=true) | Transfer learning in real life | |
+| [3-2](2-cnn.png?raw=true) | A high-level overview of a CNN | |
+| [3-3](https://ai.stanford.edu/~ang/papers/icml09-ConvolutionalDeepBeliefNetworks.pdf) | (a) Lower-level activations, followed by (b) midlevel activations and (c) upper-layer activations | Pages 5 and 7 in [Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations](https://ai.stanford.edu/~ang/papers/icml09-ConvolutionalDeepBeliefNetworks.pdf) |
+| [3-4](4-transfer-learning.png?raw=true) | An overview of transfer learning | |
+| [3-5](5-finetuning.png?raw=true) | Fine tuning a convolutional neural network | |
+| [3-6](6-folder-tree-structure.png?raw=true) | Example directory structure of the training and validation data for different classes | |
+| [3-7](7-overfitting-underfitting.png?raw=true) | Underfitting, overfitting, and ideal fitting for points close to a sine curve | |
+| [3-8](8-rabbit-augmentations.png?raw=true) | Possible image augmentations generated from a single image | |
+| [3-9](9-highest-probability-dogs.png?raw=true) | Images with the highest probability of containing dogs | |
+| [3-10](10-lowest-probability-dogs.png?raw=true) | Images with the lowest probability of containing dogs | |
+| [3-11](11-cats-highest-probability-containing-dogs.png?raw=true) | Images of cats with the highest probability of containing dogs | |
+| [3-12](12-highest-probability-cats.png?raw=true) | Images with the highest probability of containing cats | |
+| [3-13](13-lowest-probability-cats.png?raw=true) | Images with the lowest probability of containing cats | |
+| [3-14](14-dogs-highest-probability-containing-cats.png?raw=true) | Images of dogs with the highest probability of containing cats | |
+| [3-15](15-tensorflow-playground.png?raw=true) | Building a neural network in TensorFlow Playground | |
+| [3-16](16-convnetjs.png?raw=true) | Defining a CNN and visualizing the output of each layer during training in ConvNetJS | |