Author: Vincent Granville
By Dan Howarth and Ajit Jaokar, October 2019. 42 pages. Part 1 will introduce the core concepts of Deep Learning. We will also start coding straightaway with Tensorflow 2.0. In part 2, we use another dataset – the mnist dataset – to build on our knowledge. In particular, we will:
- Introduce Computer Vision
- Introduce convolutional layers into our models
- Introduce the concept of regularisation
- Introduce the validation set in training our model
- Introduce how to save and reuse our model
Contents
Part 1: Deep Learning with TensorFlow 2.0 (page 3)
1. Introduction to the Notebooks 3
2. Introduction to this Notebook 4
- Loading the Libraries 4
- Introduction to our problem 5
3. Deep Learning Conceptual Introduction 5
4. Data 7
5. Model 12
6. Training the Model 16
7. Evaluation and Inference 20
- Plotting our results 21
- Making a prediction on a single image 23
8. Summary 25
9. Exercise 25
Part 2: Computer Vision with CNNs (page 28)
1. Introduction to this Notebook 28
- Load Libraries 28
- Loading our Data 29
2. Data: Introduction to Computer Vision 29
3. Model Building 32
4. Training 36
- Saving Models 39
- Saving and Loading Weights Only 40
- Saving and Loading an entire model 41
5. Evaluation and Inference 41
6. Summary 42
7. Exercises 42
Download the book (members only)
Click here to get the book. For Data Science Central members only. If you have any issues accessing the book please contact us at info@datasciencecentral.com. To become a member, click here.