Theano (1.0.5)
Published 2026-02-24 14:09:28 +00:00 by atheaadmin
Installation
pip install --index-url About this package
Optimizing compiler for evaluating mathematical expressions on CPUs and GPUs.
Theano is a Python library that allows you to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays. It is built on top of NumPy_. Theano features:
- tight integration with NumPy: a similar interface to NumPy's. numpy.ndarrays are also used internally in Theano-compiled functions.
- transparent use of a GPU: perform data-intensive computations up to 140x faster than on a CPU (support for float32 only).
- efficient symbolic differentiation: Theano can compute derivatives for functions of one or many inputs.
- speed and stability optimizations: avoid nasty bugs when computing expressions such as log(1 + exp(x)) for large values of x.
- dynamic C code generation: evaluate expressions faster.
- extensive unit-testing and self-verification: includes tools for detecting and diagnosing bugs and/or potential problems.
Theano has been powering large-scale computationally intensive scientific research since 2007, but it is also approachable enough to be used in the classroom (IFT6266 at the University of Montreal).
.. _NumPy: http://numpy.scipy.org/
============= Release Notes
Theano 1.0.5 (27th of July 2020)
This is a maintenance release of Theano, version 1.0.5, with no
new features, but some deprecation fixes.
We recommend that everybody update to this version.
Highlights (since 1.0.4):
- Theano is now compatible with Python 3.9
- Fixed many deprecation warnings
A total of 13 people contributed to this release since 1.0.4:
- 1fish2
- Frederic Bastien
- Rebecca Palmer
- Miro Hrončok
- Dan Foreman-Mackey
- Adrian Seyboldt
- abergeron
- Tim Gates
- Tim Odonnell
- Robert P. Goldman
- Duc Nguyen
- Igor Varfolomeev
- Thomas Wiecki