`convolutional_orthogonal_2D`, `convolutional_orthogonal_3D`) have
    consistent behavior with the `tf.initializers.orthogonal` initializer, i.e.
    scale the output l2-norm by `gain` and NOT by `sqrt(gain)`. (Note that these
    functions are currently in `tf.contrib` which is not guaranteed backward
    compatible).

## Bug Fixes and Other Changes

*   Documentation