Fuel: Difference between revisions
From charlesreid1
(Created page with "=Basics= Fuel is a library for creating machine learning data pipelines. There are multiple features that make it really convenient. Find fuel on Github here: https://github...") |
|||
| Line 21: | Line 21: | ||
$ cd fuel | $ cd fuel | ||
$ python setup.py build && python setup.py install | $ python setup.py build && python setup.py install | ||
</pre> | |||
==Wrapping Custom Datasets with Fuel== | |||
Repo by github user dribnet illustrates how to wrap a new dataset using Fuel: https://github.com/dribnet/lfw_fuel | |||
<pre> | |||
from keras.models import Sequential | |||
from lfw_fuel import lfw | |||
# the data, shuffled and split between train and test sets | |||
(X_train, y_train), (X_test, y_test) = lfw.load_data(format="deepfunneled") | |||
# (build the perfect model here) | |||
model.fit(X_train, Y_train, show_accuracy=True, validation_data=(X_test, Y_test)) | |||
score = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0) | |||
</pre> | </pre> | ||
Revision as of 18:36, 5 May 2017
Basics
Fuel is a library for creating machine learning data pipelines. There are multiple features that make it really convenient.
Find fuel on Github here: https://github.com/mila-udem/fuel
Prerequisites
Fuel uses HDF5, so you will need a copy of HDF5 header files installed locally. Use your package manager, or follow HDF5 installation instructions. On a Mac:
$ brew install hdf5
Now you can install Fuel.
Install
$ git clone git@github.com:/mila-udem/fuel.git $ cd fuel $ python setup.py build && python setup.py install
Wrapping Custom Datasets with Fuel
Repo by github user dribnet illustrates how to wrap a new dataset using Fuel: https://github.com/dribnet/lfw_fuel
from keras.models import Sequential from lfw_fuel import lfw # the data, shuffled and split between train and test sets (X_train, y_train), (X_test, y_test) = lfw.load_data(format="deepfunneled") # (build the perfect model here) model.fit(X_train, Y_train, show_accuracy=True, validation_data=(X_test, Y_test)) score = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)