tf.accumulate_n(inputs, shape=None, tensor_dtype=None, name=None) Returns the element-wise sum of a list of tensors.

tf.sparse_segment_sqrt_n(data, indices, segment_ids, name=None) Computes the sum along sparse segments of a tensor divided by

tf.ifft3d(input, name=None) Compute the inverse 3-dimensional discrete Fourier Transform over the inner-most 3

tf.floordiv(x, y, name=None) Divides x / y elementwise, rounding down for floating point. The

tf.diag_part(input, name=None) Returns the diagonal part of the tensor. This operation returns

tf.mul(x, y, name=None) Returns x * y element-wise. NOTE: Mul supports broadcasting

tf.div(x, y, name=None) Returns x / y element-wise. NOTE: Div supports broadcasting

tf.self_adjoint_eig(tensor, name=None) Computes the eigen decomposition of a batch of self-adjoint matrices.

tf.self_adjoint_eigvals(tensor, name=None) Computes the eigenvalues of one or more self-adjoint matrices.

tf.reduce_mean(input_tensor, reduction_indices=None, keep_dims=False, name=None) Computes the mean of elements across dimensions