Exercises and questionnaires following the book Deep Learning for Coders with fastai and PyTorch and the 2020 version of the fastai course.
For the exercises, additional examples will be created, instead of executing what you can find in the Fastbook repo, as the purpose is to see how to apply PyTorch and fastai in different use cases.
The questionnaires solutions focus on the theoretical questions and give references for further exploration, so not all points can have an answer. The questionnaires are presented as in they appeared in the chapters of the book, which is different to the lessons in the course. Answers to the questions can be also found in the Fastai Forum Part 1 v4.
I. Deep Learning in Practice
- Your Deep Learning Journey
- From Model to Production
- Data Ethics
II. Understanding fastai’s Applications
- Under the Hood: Training a Digit Classifier
- Image Classification
- Other Computer Vision Problems
- Training a State-of-the-Art Model
- Collaborative Filtering Deep Dive
- Tabular Modeling Deep Dive
- NLP Deep Dive: RNNs
- Data Munging with fastai’s Mid-Level API
III. Foundations of Deep Learning
- A Language Model from Scratch
- Convolutional Neural Networks
- ResNets
- Application Architectures Deep Dive
- The Training Process
IV. Deep Learning from Scratch
- A Neural Net from the Foundations
- CNN Interpretation with CAM
- A fastai Learner from Scratch
- Concluding Thoughts
- Lesson 1 - Your first models
- Video
- Chapters covered: Chapter 1
- Lesson 2 - Evidence and p values
- Video
- Chapters covered: Chapter 1, Chapter 2
- Lesson 3 - Production and deployment
- Video
- Chapters covered: Chapter 4
- Lesson 4 - SGD from scratch
- Video
- Chapters covered: Chapter 4
- Lesson 5 - Data ethics
- Video
- Chapters covered: Chapter 3
- Lesson 6 - Collaborative filtering
- Video
- Chapters covered: Chapter 5, Chapter 6, Chapter 7
- Lesson 7 - Tabular data
- Video
- Chapters covered: Chapter 8, Chapter 9
- Lesson 8 - Natural language processing
- Video
- Chapters covered: Chapter 10, Chapter 12