Method LRN
LRN(TensorFloat, float, float, float, int)
Normalizes the input tensor over local input regions.
Declaration
public TensorFloat LRN(TensorFloat X, float alpha, float beta, float bias, int size)Parameters
| Type | Name | Description |
|---|---|---|
| TensorFloat | X | The input tensor. |
| float | alpha | The scaling parameter to use for the normalization. |
| float | beta | The exponent to use for the normalization. |
| float | bias | The bias value to use for the normalization. |
| int | size | The number of channels to sum over. |
Returns
| Type | Description |
|---|---|
| TensorFloat | The computed output tensor. |