minerva.losses.xtent_loss

Classes

NTXentLoss

Base class for all neural network modules.

Module Contents

class minerva.losses.xtent_loss.NTXentLoss(temperature)

Bases: torch.nn.modules.loss._Loss

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Parameters:

temperature (float)

The constructor of the NTXentLoss class.

Parameters

• temperature: float

  The temperature of the softmax function

criterion

eps = 1e-08

forward(y_0, y_1)

Forward pass of the NTXentLoss class.

Based on Lightly SSL’s implementation.

Parameters

• y_0: Tensor

  The first tensor to be compared

• y_1: Tensor

  The second tensor to be compared

Returns

• Tensor

  The loss value

Parameters:

• y_0 (torch.Tensor)

• y_1 (torch.Tensor)

Return type:

torch.Tensor

temperature