relu¶

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

Applies Rectified Linear Unit (RELU) function to each element of the input tensor:

\(\text{relu}(x) = \max(0,x)\)

Parameters:: input (Tensor) – The input tensor.
Returns:: A tensor of the same shape as the input.
Return type:: Tensor

Example

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

Local Variables¶

>>> input
tensor([1.0000, 2.0000, 3.0000, 4.0000], dtype=float32, loc=gpu:0, shape=(4,))

>>> output
tensor([1.0000, 2.0000, 3.0000, 4.0000], dtype=float32, loc=gpu:0, shape=(4,))