Appendix B. PyTorch
B.1 What is PyTorch?
PyTorch is a free, open source library used for scientific computing and deep learning applications such as computer vision and natural language processing. It is Python based and was developed by Facebook’s AI Research (FAIR) lab. PyTorch is widely used by the research community and industry practitioners. Horace He conducted a recent study (available at http://mng.bz/W7Kl) that shows that the majority of the techniques published in major machine learning conferences in 2019 were implemented in PyTorch. Other libraries and frameworks like TensorFlow, Keras, CNTK, and MXNet can be used to build and train neural networks, but we will use PyTorch in this book. The library is pythonic and utilizes Python ...
Get Interpretable AI now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
