PyTensor is a fork of Aesara, a Python library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays. PyTensor is based on Theano, which has been powering large-scale computationally intensive scientific investigations since 2007. A hackable, pure-Python codebase. Extensible graph framework is suitable for rapid development of custom operators and symbolic optimizations. Implements an extensible graph transpilation framework that currently provides compilation via C, JAX, and Numba. Based on one of the most widely-used Python tensor libraries: Theano.

Features

  • Use numpy.ndarray in PyTensor-compiled functions
  • PyTensor efficiently computes your derivatives for functions with one or many inputs
  • Get the right answer for log(1 + x) even when x is near zero
  • Evaluate expressions faster
  • Efficient symbolic differentiation
  • Speed and stability optimizations

Project Samples

PyTensor Screenshot 1

Project Activity

See All Activity >

Categories

Mathematics, Libraries, Machine Learning

License

MIT License

Follow PyTensor

PyTensor Web Site

Other Useful Business Software
MongoDB Atlas runs apps anywhere Icon
MongoDB Atlas runs apps anywhere

Deploy in 115+ regions with the modern database for every enterprise.

MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of PyTensor!

Additional Project Details

Programming Language

Python

Related Categories

Python Mathematics Software, Python Libraries, Python Machine Learning Software

Registered

2023-08-07
Report inappropriate content