Google I/O is a wrap! Catch up on TensorFlow sessions View sessions


View source on GitHub

Normalizes the given input across the specified dimension to unit length.

Note that the rank of input must be known.

inputs A Tensor of arbitrary size.
dim The dimension along which the input is normalized.
epsilon A small value to add to the inputs to avoid dividing by zero.
scope Optional scope for variable_scope.

The normalized Tensor.

ValueError If dim is smaller than the number of dimensions in 'inputs'.