Normalization class providing methods for normalization techniques.
More...
|
def | __init__ (self, int apply_norm, Optional[Tuple[int, int]] custom_min_max=None, float eps=5e-12, int p=2, int dim=0) |
| Initialize Normalization class. More...
|
|
pytorch.Tensor | apply_normalization (self, pytorch.Tensor tensor) |
| All encompassing function to perform normalization depending on the instance's apply_norm code. More...
|
|
pytorch.Tensor | min_max_normalization (self, pytorch.Tensor tensor) |
| Method to apply min-max normalization. More...
|
|
pytorch.Tensor | p_normalization (self, pytorch.Tensor tensor) |
| The p-normalization method. More...
|
|
pytorch.Tensor | standardization (self, pytorch.Tensor tensor) |
| Method to standardize the input tensor. More...
|
|
|
| apply_norm |
| The input apply_norm argument; indicating the normalisation to be used. More...
|
|
| custom_min_max |
| The input custom_min_max argument. More...
|
|
| dim |
| The input dim argument; indicating dimension along which we wish to normalise. More...
|
|
| eps |
| The input eps argument; indicating epsilon to be used for normalisation. More...
|
|
| p |
| The input p argument; indicating p-value for p-normalisation. More...
|
|
Normalization class providing methods for normalization techniques.
◆ __init__()
def rlpack.utils.normalization.Normalization.__init__ |
( |
|
self, |
|
|
int |
apply_norm, |
|
|
Optional[Tuple[int, int]] |
custom_min_max = None , |
|
|
float |
eps = 5e-12 , |
|
|
int |
p = 2 , |
|
|
int |
dim = 0 |
|
) |
| |
Initialize Normalization class.
- Parameters
-
apply_norm | int: apply_norm code for normalization. (Refer rlpack.utils.setup.Setup for more information). |
custom_min_max | Optional[Tuple[int, int]]: Tuple of custom min and max value for min-max normalization. Default: None. |
eps | float: The epsilon value for normalization (small value for numerical stability). Default: 5e-12. |
p | int: The p-value for p-normalization. Default: 2. |
dim | int: The dimension along which normalization is to be applied. Default: 0. |
◆ apply_normalization()
pytorch.Tensor rlpack.utils.normalization.Normalization.apply_normalization |
( |
|
self, |
|
|
pytorch.Tensor |
tensor |
|
) |
| |
All encompassing function to perform normalization depending on the instance's apply_norm code.
- Parameters
-
tensor | pytorch.Tensor: The tensor to apply normalization on. |
- Returns
- pytorch.Tensor: The normalized tensor.
◆ min_max_normalization()
pytorch.Tensor rlpack.utils.normalization.Normalization.min_max_normalization |
( |
|
self, |
|
|
pytorch.Tensor |
tensor |
|
) |
| |
Method to apply min-max normalization.
- Parameters
-
tensor | pytorch.Tensor: The input tensor to be min-max normalized. |
- Returns
- (pytorch.Tensor): The normalized tensor.
◆ p_normalization()
pytorch.Tensor rlpack.utils.normalization.Normalization.p_normalization |
( |
|
self, |
|
|
pytorch.Tensor |
tensor |
|
) |
| |
The p-normalization method.
- Parameters
-
tensor | pytorch.Tensor: The input tensor to be standardized. |
- Returns
- pytorch.Tensor: The p-normalized tensor.
◆ standardization()
pytorch.Tensor rlpack.utils.normalization.Normalization.standardization |
( |
|
self, |
|
|
pytorch.Tensor |
tensor |
|
) |
| |
Method to standardize the input tensor.
- Parameters
-
tensor | pytorch.Tensor: he input tensor to be standardized. |
- Returns
- pytorch.Tensor: The standardized tensor.
◆ apply_norm
rlpack.utils.normalization.Normalization.apply_norm |
The input apply_norm
argument; indicating the normalisation to be used.
◆ custom_min_max
rlpack.utils.normalization.Normalization.custom_min_max |
The input custom_min_max
argument.
Indicating the custom min-max values for min-max normalisation to be used.
◆ dim
rlpack.utils.normalization.Normalization.dim |
The input dim
argument; indicating dimension along which we wish to normalise.
◆ eps
rlpack.utils.normalization.Normalization.eps |
The input eps
argument; indicating epsilon to be used for normalisation.
rlpack.utils.normalization.Normalization.p |
The input p
argument; indicating p-value for p-normalisation.