torchlayers.activations module¶
-
class
torchlayers.activations.
HardSigmoid
[source]¶ Applies HardSigmoid function element-wise.
Uses
torch.nn.functional.hardtanh
internally with0
and1
ranges.- Parameters
tensor (torch.Tensor) – Tensor activated element-wise
-
forward
(tensor: torch.Tensor)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
class
torchlayers.activations.
HardSwish
[source]¶ Applies HardSwish function element-wise.
While similar in effect to
Swish
should be more CPU-efficient. Above formula proposed by in Andrew Howard et. al in Searching for MobileNetV3.- Parameters
tensor (torch.Tensor) – Tensor activated element-wise
-
forward
(tensor: torch.Tensor)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
class
torchlayers.activations.
Swish
(beta: float = 1.0)[source]¶ Applies Swish function element-wise.
This form was originally proposed by Prajit Ramachandran et. al in Searching for Activation Functions
- Parameters
beta (float, optional) – Multiplier used for sigmoid. Default: 1.0 (no multiplier)
-
forward
(tensor: torch.Tensor)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
torchlayers.activations.
hard_sigmoid
(tensor: torch.Tensor, inplace: bool = False) → torch.Tensor[source]¶ Applies HardSigmoid function element-wise.
See
torchlayers.activations.HardSigmoid
for more details.- Parameters
tensor (torch.Tensor) – Tensor activated element-wise
inplace (bool, optional) – Whether operation should be performed
in-place
. Default:False
- Returns
- Return type
-
torchlayers.activations.
hard_swish
(tensor: torch.Tensor) → torch.Tensor[source]¶ Applies HardSwish function element-wise.
See
torchlayers.activations.HardSwish
for more details.- Parameters
tensor (torch.Tensor) – Tensor activated element-wise
- Returns
- Return type
-
torchlayers.activations.
swish
(tensor: torch.Tensor, beta: float = 1.0) → torch.Tensor[source]¶ Applies Swish function element-wise.
See
torchlayers.activations.Swish
for more details.- Parameters
tensor (torch.Tensor) – Tensor activated element-wise
beta (float, optional) – Multiplier used for sigmoid. Default: 1.0 (no multiplier)
- Returns
- Return type