tfa.activations.hardshrink

Hard shrink function.

tfa.activations.hardshrink(
    x: tfa.types.TensorLike,
    lower: tfa.types.Number = -0.5,
    upper: tfa.types.Number = 0.5
) -> tf.Tensor

Computes hard shrink function:

\[ \mathrm{hardshrink}(x) = \begin{cases} x & \text{if } x < \text{lower} \\ x & \text{if } x > \text{upper} \\ 0 & \text{otherwise} \end{cases}. \]

x = tf.constant([1.0, 0.0, 1.0])
tfa.activations.hardshrink(x)
<tf.Tensor: shape=(3,), dtype=float32, numpy=array([1., 0., 1.], dtype=float32)>

Args
`x`	A `Tensor`. Must be one of the following types: `bfloat16`, `float16`, `float32`, `float64`.
`lower`	`float`, lower bound for setting values to zeros.
`upper`	`float`, upper bound for setting values to zeros.

Returns
A `Tensor`. Has the same type as `x`.

Args