tf.raw_ops.InvGrad

Computes the gradient for the inverse of x wrt its input.

Specifically, grad = -dy * y*y, where y = 1/x, and dy is the corresponding input gradient.

yA Tensor. Must be one of the following types: bfloat16, half, float32, float64, complex64, complex128.
dyA Tensor. Must have the same type as y.
nameA name for the operation (optional).

A Tensor. Has the same type as y.