This python library provides an API for learning hierarchical primitives from demonstration using Tensorflow.
The packackge requires the following dependencies:
appnope==0.1.0
atari-py==0.0.18
box2d-py==2.3.1
cloudpickle==0.2.2
colorama==0.3.7
cycler==0.10.0
dask==0.13.0
decorator==4.0.10
flatbuffers==2015.12.22.1
funcsigs==1.0.2
future==0.16.0
-e git+https://github.com/openai/gym@443d509df71eed4a153f6588bfcedf1f3fe6baff#egg=gym
hyperopt==0.1
imageio==2.1.2
ipython==5.2.1
ipython-genutils==0.1.0
joblib==0.10.3
Keras==1.2.1
matplotlib==1.5.3
mujoco-py==0.5.7
networkx==1.11
nose==1.3.7
numpy==1.11.2
olefile==0.44
pachi-py==0.0.21
packaging==16.8
pexpect==4.2.1
pickleshare==0.7.4
Pillow==4.0.0
prompt-toolkit==1.0.10
protobuf==3.1.0.post1
psutil==5.1.0
ptyprocess==0.5.1
pyglet==1.2.4
Pygments==2.2.0
pymongo==3.4.0
PyOpenGL==3.1.0
pyparsing==2.1.10
python-dateutil==2.5.3
pytz==2016.7
PyYAML==3.12
redis==2.10.5
requests==2.13.0
scikit-image==0.12.3
scikit-learn==0.18
scipy==0.18.1
simplegeneric==0.8.1
six==1.10.0
sklearn==0.0
tensorflow==0.12.0rc1
Theano==0.8.2
toolz==0.8.2
traitlets==4.3.1
wcwidth==0.1.7
ray==0.1.2
Once the dependencies are installed the first step is to create a virtual environment
virtualenv segment
Activate the virtual environment
cd segment
source bin/activate
Clone the git repo
git clone https://sjyk@bitbucket.org/sjyk/segment-centroid.git