ttnn.softshrink

ttnn.softshrink(input_tensor: ttnn.Tensor, *, lambd: float = 0.5, memory_config: ttnn.MemoryConfig = None, output_tensor: ttnn.Tensor = None, sub_core_grids: ttnn.CoreRangeSet = None) → ttnn.Tensor

Applies softshrink to input_tensor element-wise with lambd.

The lambda parameter for the softshrink function

\[\mathrm{output\_tensor}_i = \verb|softshrink|(\mathrm{input\_tensor}_i, \verb|lambd|)\]

Parameters:

input_tensor (ttnn.Tensor) – the input tensor.

Keyword Arguments:

lambd (float) – Defaults to 0.5.
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 for the operation. Defaults to None.

Returns:

ttnn.Tensor – the output tensor.

Note

Supported dtypes and layouts:

Dtypes	Layouts
FLOAT32, BFLOAT16, BFLOAT8_B	TILE, ROW_MAJOR

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 soft shrinkage function
output = ttnn.softshrink(tensor, lambd=5)
logger.info(f"Soft shrink: {output}")