TensorX is a minimalistic utility library to build neural network models in TensorFlow
Project description
TensorX is an free and open-source minimalistic high-level library to build, train, and run neural network models in TensorFlow. This is currently under heavy development, as such I don't recommend it's usage yet. Tensorflow is approaching a new release and there will be a split in this library as well that will accomodate both static graphs and eager execution (the new default mode).
Documentation will be available at tensorx.readthedocs.io.
Installation
TensorX is compatible with Python 3.5+. It depends on Tensorflow and pygraphviz but will not be shipping with tensorflow as a dependency. The reason for this is that tensorflow might come under different packages depending on whether or not the user is using GPU hardware. Moreover, you might want to use a custom tensorflow build. For these reasons Tensorflow should be installed separately from tensorx.
pip install tensorflow
# pip install tensorflow-gpu
pip install tensorx
virtualenv: much like tensorflow, virtualenv is recommended to install tensorx in its own environment to avoid interfering with system-wide packages.
Getting Started
Documentation and tutorials will be coming soon
Author
- Davide Nunes: get in touch @davidelnunes
License
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
