tf.contrib.nn.nth_element( input, n, reverse=False, name=None )
Finds values of the
n-th order statistic for the last dmension.
If the input is a vector (rank-1), finds the entries which is the nth-smallest value in the vector and outputs their values as scalar tensor.
For matrices (resp. higher rank input), computes the entries which is the nth-smallest value in each row (resp. vector along the last dimension). Thus,
values.shape = input.shape[:-1]
input: 1-D or higher
Tensorwith last dimension at least
int32. 0-D. Position of sorted vector to select along the last dimension (along each row for matrices). Valid range of n is
reverse: An optional
bool. Defaults to
False. When set to True, find the nth-largest value in the vector and vice versa.
name: A name for the operation (optional).
Tensor. Has the same type as
n-th order statistic along each last dimensional slice.