Skip to main content

A library of neural nets in theano

Project description

The theanets package provides tools for defining and optimizing several common types of neural network models. It uses Python for rapid development, and under the hood Theano provides graph optimization and fast computations on the GPU.

The package defines models for classification, autoencoding, regression, and prediction. Models can easily be created with any number of feedforward or recurrent layers and combined with different regularizers:

  • L1/L2 weight decay

  • L1/L2 hidden activation penalties (e.g., sparse autoencoders)

  • Dropout/gaussian noise (e.g., denoising autoencoders)

Several optimization algorithms are also included:


Install the latest published code using pip:

pip install theanets

Or download the current source and run it from there:

git clone
cd theanets
python develop


Let’s say you wanted to create a classifier and train it on some 100-dimensional data points that you’ve classified into 10 categories. You can define your model and train it using a few lines of code:

import climate
import theanets
import my_data_set


exp = theanets.Experiment(
    layers=(100, 200, 100, 10),


The trained network lets you make predictions on unseen test data.

More Information



Mailing list:!forum/theanets

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

theanets-0.5.3.tar.gz (43.5 kB view hashes)

Uploaded Source

Built Distributions

theanets-0.5.3-py3-none-any.whl (48.6 kB view hashes)

Uploaded Python 3

theanets-0.5.3-py2-none-any.whl (48.6 kB view hashes)

Uploaded Python 2

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page