timm/layers/evo_norm.py [139:167]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(self, num_features, apply_act=True, momentum=0.1, eps=1e-5, **_):
        super().__init__()
        self.apply_act = apply_act  # apply activation (non-linearity)
        self.momentum = momentum
        self.eps = eps
        self.weight = nn.Parameter(torch.ones(num_features))
        self.bias = nn.Parameter(torch.zeros(num_features))
        self.register_buffer('running_var', torch.ones(num_features))
        self.reset_parameters()

    def reset_parameters(self):
        nn.init.ones_(self.weight)
        nn.init.zeros_(self.bias)

    def forward(self, x):
        _assert(x.dim() == 4, 'expected 4D input')
        x_dtype = x.dtype
        v_shape = (1, -1, 1, 1)
        if self.apply_act:
            if self.training:
                var = x.float().var(dim=(0, 2, 3), unbiased=False)
                n = x.numel() / x.shape[1]
                self.running_var.copy_(
                    self.running_var * (1 - self.momentum) +
                    var.detach().to(self.running_var.dtype) * self.momentum * (n / (n - 1)))
            else:
                var = self.running_var
            var = var.to(x_dtype).view(v_shape)
            left = var.add(self.eps).sqrt_()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



timm/layers/evo_norm.py [174:202]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(self, num_features, apply_act=True, momentum=0.1, eps=1e-5, **_):
        super().__init__()
        self.apply_act = apply_act  # apply activation (non-linearity)
        self.momentum = momentum
        self.eps = eps
        self.weight = nn.Parameter(torch.ones(num_features))
        self.bias = nn.Parameter(torch.zeros(num_features))
        self.register_buffer('running_var', torch.ones(num_features))
        self.reset_parameters()

    def reset_parameters(self):
        nn.init.ones_(self.weight)
        nn.init.zeros_(self.bias)

    def forward(self, x):
        _assert(x.dim() == 4, 'expected 4D input')
        x_dtype = x.dtype
        v_shape = (1, -1, 1, 1)
        if self.apply_act:
            if self.training:
                var = x.float().var(dim=(0, 2, 3), unbiased=False)
                n = x.numel() / x.shape[1]
                self.running_var.copy_(
                    self.running_var * (1 - self.momentum) +
                    var.detach().to(self.running_var.dtype) * self.momentum * (n / (n - 1)))
            else:
                var = self.running_var
            var = var.to(x_dtype).view(v_shape)
            left = var.add(self.eps).sqrt_()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -