DEV Community

Super Kai (Kazuya Ito)
Super Kai (Kazuya Ito)

Posted on • Edited on

1

SELU and CELU in PyTorch

Buy Me a Coffee

*Memos:

SELU() can get the 0D or more D tensor of the zero or more values computed by SELU function from the 0D or more D tensor of zero or more elements as shown below:

*Memos:

  • The 1st argument for initialization is inplace(Optional-Default:False-Type:bool): *Memos:
    • It does in-place operation.
    • Keep it False because it's problematic with True.
  • The 1st argument is input(Required-Type:tensor of float).

Image description

import torch
from torch import nn

my_tensor = torch.tensor([8., -3., 0., 1., 5., -2., -1., 4.])

selu = nn.SELU()
selu(input=my_tensor)
# tensor([8.4056, -1.6706, 0.0000, 1.0507, 5.2535, -1.5202, -1.1113, 4.2028])

selu
# SELU()

selu.inplace
# False

selu = nn.SELU(inplace=True)
selu(input=my_tensor)
# tensor([8.4056, -1.6706, 0.0000, 1.0507, 5.2535, -1.5202, -1.1113, 4.2028])

my_tensor = torch.tensor([[8., -3., 0., 1.],
                          [5., -2., -1., 4.]])
selu = nn.SELU()
selu(input=my_tensor)
# tensor([[8.4056, -1.6706, 0.0000, 1.0507],
#         [5.2535, -1.5202, -1.1113, 4.2028]])

my_tensor = torch.tensor([[[8., -3.], [0., 1.]],
                          [[5., -2.], [-1., 4.]]])
selu = nn.SELU()
selu(input=my_tensor)
# tensor([[[8.4056, -1.6706], [0.0000, 1.0507]],
#         [[5.2535, -1.5202], [-1.1113, 4.2028]]])
Enter fullscreen mode Exit fullscreen mode

CELU() can get the 0D or more D tensor of the zero or more values computed by CELU function from the 0D or more D tensor of zero or more elements as shown below:

*Memos:

  • The 1st argument for initialization is alpha(Optional-Default:1.0-Type:float). *It's applied to negative input values.
  • The 2nd argument for initialization is inplace(Optional-Default:False-Type:bool): *Memos:
    • It does in-place operation.
    • Keep it False because it's problematic with True.
  • The 1st argument is input(Required-Type:tensor of float).

Image description

import torch
from torch import nn

my_tensor = torch.tensor([8., -3., 0., 1., 5., -2., -1., 4.])

celu = nn.CELU()
celu(input=my_tensor)
# tensor([8.0000, -0.9502, 0.0000, 1.0000, 5.0000, -0.8647, -0.6321, 4.0000])

celu
# CELU(alpha=1.0)

celu.alpha
# 1.0

celu.inplace
# False

celu = nn.CELU(alpha=1.0, inplace=True)
celu(input=my_tensor)
# tensor([8.0000, -0.9502, 0.0000, 1.0000, 5.0000, -0.8647, -0.6321, 4.0000])

my_tensor = torch.tensor([[8., -3., 0., 1.],
                          [5., -2., -1., 4.]])
celu = nn.CELU()
celu(input=my_tensor)
# tensor([[8.0000, -0.9502, 0.0000, 1.0000],
#         [5.0000, -0.8647, -0.6321, 4.0000]])

my_tensor = torch.tensor([[[8., -3.], [0., 1.]],
                          [[5., -2.], [-1., 4.]]])
celu = nn.CELU()
celu(input=my_tensor)
# tensor([[[8.0000, -0.9502], [0.0000, 1.0000]],
#         [[5.0000, -0.8647], [-0.6321, 4.0000]]])
Enter fullscreen mode Exit fullscreen mode

Heroku

Build apps, not infrastructure.

Dealing with servers, hardware, and infrastructure can take up your valuable time. Discover the benefits of Heroku, the PaaS of choice for developers since 2007.

Visit Site

Top comments (0)