By Dan Howarth and Ajit Jaokar, October 2019. 58 pages. CNN stands for Convolutional Neural Networks. 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
1. Introduction to the Notebooks
2. Introduction to this Notebook
- Loading the Libraries
- Introduction to our problem
3. Deep Learning Conceptual Introduction
4. Data
5. Model
6. Training the Model
7. Evaluation and Inference
- Plotting our results
- Making a prediction on a single image
8. Summary
9. Exercise
Part 2: Computer Vision with CNNs
1. Introduction to this Notebook
- Load Libraries
- Loading our Data
2. Data: Introduction to Computer Vision
3. Model Building
4. Training
- Saving Models
- Saving and Loading Weights Only
- Saving and Loading an entire model
5. Evaluation and Inference
6. Summary
7. Exercises
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 [email protected] To become a member, click here.