tf.raw_ops.TanhGrad

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

tf.raw_ops.TanhGrad(
    y, dy, name=None
)

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

Args:

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

Returns:

A Tensor. Has the same type as y.