silu¶

nvtripy.silu(input: Tensor) → Tensor[source]¶

Applies the Sigmoid Linear Unit (SiLU) function to each element of the input tensor. This function is also known as the swish function.

\(\text{silu}(x) = x \cdot \sigma (x)\) where \(\sigma (x)_i = \frac{1}{1 + \exp{-x_i}}\)

Parameters:: input (Tensor) – [dtype=T1] The input tensor.
Returns:: [dtype=T1] A tensor of the same shape as the input.
Return type:: Tensor

DATA TYPE CONSTRAINTS:

T1: float16, bfloat16, float32

Example

input = tp.Tensor([1.0, 2.0, 3.0, 4.0], dtype=tp.float32)
output = tp.silu(input)

Local Variables¶

>>> input
tensor([1, 2, 3, 4], dtype=float32, loc=cpu:0, shape=(4,))

>>> output
tensor([0.731059, 1.76159, 2.85772, 3.92806], dtype=float32, loc=gpu:0, shape=(4,))