在读《Deep Learning for Coders with fastai and PyTorch》 🌕🌕🌕🌕🌕
Jeremy的学习思路很赞,类似Bidirectional BFS。先学一点model from scratch (simple 3-layer NN) & fastai lib (transfer ResNet34), 然后bottom-up & top-down,同时深入学习,当交汇的时候就说明完整掌握了。
全书就是 Jupyter Notebook: github.com/fastai/fastbook/clean/. 直接在 Colab打开 (runtime改为GPU即可, 利用transfer learning, 所以免费instance即可)
课程见https://course.fast.ai/ 有2020版part 1
AI学术界很多Jargon,写成code就通俗易懂了。
Book
Deep Learning for Coders with fastai and PyTorch
Douban GoodreadsDeep learning has the reputation as an exclusive domain for math PhDs. Not so. With this book, programmers comfortable with Python will learn how to get started with deep learning right away.
Using PyTorch and the fastai deep learning library, you’ll learn how to train a model to accomplish a wide range of tasks—including computer vision, natural language processing, tabular data, and generative networks. At the same time, you’ll dig progressively into deep learning theory so that by the end of the book you’ll have a complete understanding of the math behind the library’s functions.