ttnn.softshrink

ttnn.softshrink = FastOperation(python_fully_qualified_name='ttnn.softshrink', function=<ttnn._ttnn.operations.unary.softshrink_t object>, preprocess_golden_function_inputs=<function default_preprocess_golden_function_inputs>, golden_function=<function _golden_function_softshrink>, postprocess_golden_function_outputs=<function default_postprocess_golden_function_outputs>, is_cpp_operation=True, is_experimental=False)

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