Keras Tutorial

KerasInstallGist.txt

Today I did a walkthrough on getting Keras installed. Keras is an abstraction on Tensorflow & Theano which are deep learning frameworks. 

http://machinelearningmastery.com/introduction-python-deep-learning-library-keras/

[Chris@/Users/Chris]$ sudo pip install keras
Collecting keras
  Downloading Keras-1.2.1.tar.gz (173kB)
    100% |████████████████████████████████| 174kB 1.6MB/s 
Collecting theano (from keras)
  Downloading Theano-0.8.2.tar.gz (2.9MB)
    100% |████████████████████████████████| 2.9MB 240kB/s 
Requirement already satisfied: pyyaml in ./anaconda/lib/python3.5/site-packages (from keras)
Requirement already satisfied: six in ./anaconda/lib/python3.5/site-packages (from keras)
Requirement already satisfied: numpy>=1.7.1 in ./anaconda/lib/python3.5/site-packages (from theano->keras)
Requirement already satisfied: scipy>=0.11 in ./anaconda/lib/python3.5/site-packages (from theano->keras)
Installing collected packages: theano, keras
  Running setup.py install for theano ... done
  Running setup.py install for keras ... done
Successfully installed keras-1.2.1 theano-0.8.2

[Chris@/Users/Chris]$ pip list | grep tensorflow
DEPRECATION: The default format will switch to columns in the future. You can use --format=(legacy|columns) (or define a format=(legacy|columns) in your pip.conf under the [list] section) to disable this warning.
tensorflow (0.12.1)

[Chris@/Users/Chris]$ mkdir .keras
[Chris@/Users/Chris]$ vim ~/.keras/keras.json


  1 {
  2     "image_dim_ordering": "tf",
  3     "epsilon": 1e-07, 
  4     "floatx": "float32",
  5     "backend": "tensorflow"
  6 }   

[Chris@/Users/Chris]$ python
Python 3.5.2 |Anaconda 4.1.1 (x86_64)| (default, Jul  2 2016, 17:52:12) 
[GCC 4.2.1 Compatible Apple LLVM 4.2 (clang-425.0.28)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> from keras import backend
Using TensorFlow backend.
>>> print backend._BACKEND
  File "<stdin>", line 1
    print backend._BACKEND
                ^
SyntaxError: Missing parentheses in call to 'print'
>>> print(backend._BACKEND)
tensorflow
>>> quit()


http://machinelearningmastery.com/tutorial-first-neural-network-python-keras/