PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing. It is primarily developed by Facebook’s AI Research lab (FAIR). It is free and open-source software released under the Modified BSD license. Although the Python interface is more polished and the primary focus of development, PyTorch also has a C++ interface.
PyTorch Capabilities & Features
- Tensor computation (similar to numpy) with strong GPU acceleration
- Deep Neural Networks built on a tape-based autodiff system
- Python-First approach, allows popular libraries and packages to be used for crafting neural network layers
- torch.distributed backend allows scalable distributed training and performance
PyTorch is extremely powerful for creating computational graphs. PyTorch relies on dynamic graphs and allows define and manipulate graph on-the-fly.This feature is what makes PyTorch a extremely powerful tool for researcher, particularly when developing Recurrent Neural Networks (RNNs).