PyTorch is an open source machine learning library. The name PyTorch comes from python, its main programming language, and the Torch library on which PyTorch is based. PyTorch has been gaining popularity among developers since its release in 2016, with features such as ease of use and flexibility, ease of debugging, high speed and community support.
The PyTorch, developed by Facebook, is similar to Google’s TensorFlow in that it works on “Tensor.” However, Whereas TensorFlow uses static calculation graphs, PyTorch uses dynamic calculation graphs.
If you’re learning about PyTorch and want to start programming, the following list of resources should help.
Programming PyTorch for Deep Learning: Creating and Deploying Deep Learning Applications This book helps you learn PyTorch by introducing how to set up PyTorch in a cloud-based environment.
This article was reprinted on February 27, 2020 in TechRepublic Japan. You can read more at TechRepublic Japan.