|TensorFlow 1 version||View source on GitHub|
Computes the norm of vectors, matrices, and tensors.
See Migration guide for more details.
tf.norm( tensor, ord='euclidean', axis=None, keepdims=None, name=None )
This function can compute several different vector norms (the 1-norm, the Euclidean or 2-norm, the inf-norm, and in general the p-norm for p > 0) and matrix norms (Frobenius, 1-norm, 2-norm and inf-norm).
ord: Order of the norm. Supported values are
np.infand any positive real number yielding the corresponding p-norm. Default is
'euclidean'which is equivalent to Frobenius norm if
tensoris a matrix and equivalent to 2-norm for vectors. Some restrictions apply: a) The Frobenius norm
'fro'is not defined for vectors, b) If axis is a 2-tuple (matrix norm), only
np.infare supported. See the description of
axison how to compute norms for a batch of vectors or matrices stored in a tensor.
None(the default), the input is considered a vector and a single vector norm is computed over the entire set of values in the tensor, i.e.
norm(tensor, ord=ord)is equivalent to
norm(reshape(tensor, [-1]), ord=ord). If
axisis a Python integer, the input is considered a batch of vectors, and
axisdetermines the axis in
tensorover which to compute vector norms. If
axisis a 2-tuple of Python integers it is considered a batch of matrices and
axisdetermines the axes in
tensorover which to compute a matrix norm. Negative indices are supported. Example: If you are passing a tensor that can be either a matrix or a batch of matrices at runtime, pass
axis=Noneto make sure that matrix norms are computed.
keepdims: If True, the axis indicated in
axisare kept with size 1. Otherwise, the dimensions in
axisare removed from the output shape.
name: The name of the op.
Tensorof the same type as tensor, containing the vector or matrix norms. If
keepdimsis True then the rank of output is equal to the rank of
tensor. Otherwise, if
axisis none the output is a scalar, if
axisis an integer, the rank of
outputis one less than the rank of
axisis a 2-tuple the rank of
outputis two less than the rank of
Mostly equivalent to numpy.linalg.norm.
Not supported: ord <= 0, 2-norm for matrices, nuclear norm.
a) If axis is
None, treats the flattened
tensor as a vector
regardless of rank.
b) Explicitly supports 'euclidean' norm as the default, including for
higher order tensors.