Dassl.pytorch/dassl/modeling/ops/efdmix.py [60:92]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(self, p=0.5, alpha=0.1, eps=1e-6, mix="random"):
        """
        Args:
          p (float): probability of using MixStyle.
          alpha (float): parameter of the Beta distribution.
          eps (float): scaling parameter to avoid numerical issues.
          mix (str): how to mix.
        """
        super().__init__()
        self.p = p
        self.beta = torch.distributions.Beta(alpha, alpha)
        self.eps = eps
        self.alpha = alpha
        self.mix = mix
        self._activated = True

    def __repr__(self):
        return (
            f"MixStyle(p={self.p}, alpha={self.alpha}, eps={self.eps}, mix={self.mix})"
        )

    def set_activation_status(self, status=True):
        self._activated = status

    def update_mix_method(self, mix="random"):
        self.mix = mix

    def forward(self, x):
        if not self.training or not self._activated:
            return x

        if random.random() > self.p:
            return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



Dassl.pytorch/dassl/modeling/ops/mixstyle.py [60:92]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(self, p=0.5, alpha=0.1, eps=1e-6, mix="random"):
        """
        Args:
          p (float): probability of using MixStyle.
          alpha (float): parameter of the Beta distribution.
          eps (float): scaling parameter to avoid numerical issues.
          mix (str): how to mix.
        """
        super().__init__()
        self.p = p
        self.beta = torch.distributions.Beta(alpha, alpha)
        self.eps = eps
        self.alpha = alpha
        self.mix = mix
        self._activated = True

    def __repr__(self):
        return (
            f"MixStyle(p={self.p}, alpha={self.alpha}, eps={self.eps}, mix={self.mix})"
        )

    def set_activation_status(self, status=True):
        self._activated = status

    def update_mix_method(self, mix="random"):
        self.mix = mix

    def forward(self, x):
        if not self.training or not self._activated:
            return x

        if random.random() > self.p:
            return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -