ttnn.normalize_global

ttnn.normalize_global(input_tensor: ttnn.Tensor, *, memory_config: ttnn.MemoryConfig = None) → ttnn.Tensor

Performs normalize_global function on input_tensor.

\[\mathrm{{output\_tensor}}_i = \verb|normalize_global|(\mathrm{{input\_tensor}}_i)\]

Parameters:

input_tensor (ttnn.Tensor) – the input tensor.

Keyword Arguments:

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

Returns:

ttnn.Tensor – the output tensor.

Note

Supported dtypes, layouts, and ranks:

Dtypes	Layouts	Ranks
BFLOAT16	ROW_MAJOR, TILE	4

Example

# Create a tensor with random values
tensor = ttnn.rand([1, 1, 32, 32], dtype=ttnn.bfloat16, layout=ttnn.TILE_LAYOUT, device=device)

# Normalize globally across all dimensions
output = ttnn.normalize_global(tensor)
logger.info(f"Normalize global: {output}")