Copyright (C) 2018 AutoML Group
This a very early pre-alpha version of our upcoming Auto-PyTorch. So far, Auto-PyTorch only supports featurized data.
Clone repository
$ cd install/path
$ git clone https://github.com/automl/Auto-PyTorch.git
$ cd Auto-PyTorch
If you want to contribute to this repository switch to our current develop branch
$ git checkout develop
Install pytorch: https://pytorch.org/
Install autonet
$ python setup.py install
In a nutshell:
from autoPyTorch import AutoNetClassification
# data and metric imports
import sklearn.model_selection
import sklearn.datasets
import sklearn.metrics
X, y = sklearn.datasets.load_digits(return_X_y=True)
X_train, X_test, y_train, y_test = \
sklearn.model_selection.train_test_split(X, y, random_state=1)
# running Auto-PyTorch
autoPyTorch = AutoNetClassification(log_level='info', max_runtime=300, min_budget=30, max_budget=90)
autoPyTorch.fit(X_train, y_train, validation_split=0.3)
y_pred = autoPyTorch.predict(X_test)
print("Accuracy score", sklearn.metrics.accuracy_score(y_test, y_pred))
More examples with datasets:
$ cd examples/
This program is free software: you can redistribute it and/or modify it under the terms of the 3-clause BSD license (please see the LICENSE file).
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
You should have received a copy of the 3-clause BSD license along with this program (see LICENSE file). If not, see https://opensource.org/licenses/BSD-3-Clause.
@incollection{mendoza-automlbook18a,
author = {Hector Mendoza and Aaron Klein and Matthias Feurer and Jost Tobias Springenberg and Matthias Urban and Michael Burkart and Max Dippel and Marius Lindauer and Frank Hutter},
title = {Towards Automatically-Tuned Deep Neural Networks},
year = {2018},
month = dec,
editor = {Hutter, Frank and Kotthoff, Lars and Vanschoren, Joaquin},
booktitle = {AutoML: Methods, Sytems, Challenges},
publisher = {Springer},
chapter = {7},
pages = {141--156},
note = {To appear.},
}
Auto-PyTorch is developed by the AutoML Group of the University of Freiburg.