torch for R
An open source machine learning framework based on PyTorch.
torch provides fast array computation with strong GPU acceleration and a neural networks library built on a tape-based autograd system. The ‘torch for R’ ecosystem is a collection of extensions for torch.
Dive in
Learn torch basics, from tensors via automatic differentiation to neural network modules.
Start with the basics in our quick tour of torch. Learn how to create tensors, use the autograd feature and build your first deep learning model.
Check out applied examples in the areas of image processing, time series forecasting, natural language processing, and more.
The Posit AI blog is the go-to page for news about the ‘torch for R’ project as well as application examples.
Need help?
Please file an issue on GitHub or use the Posit community forum.