ttnn.selu

ttnn.selu(input_tensor: ttnn.Tensor, *, scale: float = 1.0507, alpha: float = 1.67326, memory_config: ttnn.MemoryConfig = None, output_tensor: ttnn.Tensor = None, sub_core_grids: ttnn.CoreRangeSet = None) → ttnn.Tensor

Performs selu function on input_tensor.

Parameters:

input_tensor (ttnn.Tensor) – the input tensor.

Keyword Arguments:

• scale (float, optional) – Scale value. Defaults to 1.0507.

• alpha (float, optional) – Alpha value. Defaults to 1.67326.

• memory_config (ttnn.MemoryConfig, optional) – Memory configuration for the operation. Defaults to None.

• output_tensor (ttnn.Tensor, optional) – preallocated output tensor. Defaults to None.

• sub_core_grids (ttnn.CoreRangeSet, optional) – Sub-core grids. Defaults to None.

Returns:

ttnn.Tensor – the output tensor.

Example

# Create a tensor with specific values
tensor = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16),
    dtype=ttnn.bfloat16,
    layout=ttnn.TILE_LAYOUT,
    device=device,
)

# Apply SELU activation function
output = ttnn.selu(tensor, scale=1.0507, alpha=1.67326)
logger.info(f"SELU: {output}")