ttnn.logit

ttnn.logit(input_tensor: ttnn.Tensor, *, eps: float = None, memory_config: ttnn.MemoryConfig = None) → ttnn.Tensor

Performs logit function on input_tensor, eps.

Parameters:

input_tensor (ttnn.Tensor) – the input tensor.

Keyword Arguments:

• eps (float, optional) – The epsilon for input clamp bound. Defaults to None.

• 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
FLOAT32, BFLOAT16, BFLOAT8_B	TILE	2, 3, 4

Example

>>> tensor = ttnn.from_torch(torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), dtype=ttnn.bfloat16, layout=ttnn.TILE_LAYOUT, device=device)
>>> output = ttnn.logit(tensor, eps = None)

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,
)

# Compute the logit function
output = ttnn.logit(tensor, eps=5)
logger.info(f"Logit: {output}")