tf.einsum(axes, *inputs) A generalized contraction between tensors of arbitrary dimension. Like

tf.round(x, name=None) Rounds the values of a tensor to the nearest integer, element-wise. For

tf.exp(x, name=None) Computes exponential of x element-wise. \(y = e^x\). Args:

tf.cross(a, b, name=None) Compute the pairwise cross product. a and b

tf.matrix_band_part(input, num_lower, num_upper, name=None) Copy a tensor setting everything outside a central band in each innermost

tf.abs(x, name=None) Computes the absolute value of a tensor. Given a tensor of real numbers x

tf.reduce_logsumexp(input_tensor, reduction_indices=None, keep_dims=False, name=None) Computes log(sum(exp(elements across dimensions

tf.zeta(x, q, name=None) Compute the Hurwitz zeta function \(\zeta(x, q)\). The Hurwitz zeta function

tf.floor(x, name=None) Returns element-wise largest integer not greater than x. Args:

tf.matrix_solve_ls(matrix, rhs, l2_regularizer=0.0, fast=True, name=None) Solves one or more linear least-squares problems.