skip to navigation
skip to content

nolearn 0.5b1

scikit-learn compatible wrappers for neural net libraries, and other utilities.

Package Documentation

Latest Version: 0.6.0

nolearn contains a number of wrappers around existing neural network libraries, along with a few machine learning utility modules. Most functionality is written to be compatible with the the excellent scikit-learn library.

View the documentation here.

Change History

0.5b1 - 2014-08-09

  • overfeat: Add OverFeat-based feature extractor.
  • caffe: Add feature extractor based on ImageNet-pretrained nets found in caffe.

0.4 - 2014-01-15

  • cache: Use joblib’s numpy_pickle instead of cPickle to persist.

0.3.1 - 2013-11-18

  • convnet: Add center_only and classify_direct options.

0.3 - 2013-11-02

  • convnet: Add scikit-learn estimator based on Jia and Donahue’s DeCAF.
  • dbn: Change default args of use_re_lu=True and nesterov=True.

0.2 - 2013-03-03

  • dbn: Add parameters learn_rate_decays and learn_rate_minimums, which allow for decreasing the learning after each epoch of fine-tuning.
  • dbn: Allow -1 as the value of the input and output layers of the neural network. The shapes of X and y will then be used to determine those.
  • dbn: Add support for processing sparse input data matrices.
  • dbn: Improve miserable speed of DBN.predict_proba.

0.2b1 - 2012-12-30

  • Added a scikit-learn estimator based on George Dahl’s gdbn in nolearn.dbn.
File Type Py Version Uploaded on Size
nolearn-0.5b1.tar.gz (md5) Source 2014-08-29 30KB