Added an AlexNet wrapper using LRP layer definitions.

[ruthcfong]

1. modules/convolution.py was modified to support a) multiple kernel groups, per AlexNet's original architecture, and b) initialization of weights/biases with passed-in arrays (older code should still work).

2. models/alexnet.py allows pre-trained weights to be loaded. (Weights can be downloaded from http://www.cs.toronto.edu/~guerzhoy/tf_alexnet/bvlc_alexnet.npy)

Note: This implementation is based on https://github.com/guerzh/tf_weights, which doesn't work perfectly / seems to do well on some images but not others, as noted at https://github.com/guerzh/tf_weights/issues/.

3. examples/alexnet_demo.py I've included demo code and two example images that demonstrate a correctly behaving (examples/poodle.png) and incorrectly behaving (examples/doberman.png) classification result.

4. __init__.py and models/__init__.py This allows /path/to/interprettensor to be exported to PYTHONPATH and modules and models to be called as done in examples/alexnet_demo.py Example: export PYTHONPATH="/data/ruthfong/tensorflow/interprettensor":$PYTHONPATH