layers.py 文件源码

def forward_pass(self, X, training=True):

        # Initialize running mean and variance if first run
        if self.running_mean is None:
            self.running_mean = np.mean(X, axis=0)
            self.running_var = np.var(X, axis=0)

        if training:
            mean = np.mean(X, axis=0)
            var = np.var(X, axis=0)
            self.X_centered = X - mean
            self.stddev_inv = 1 / np.sqrt(var + self.eps)
            self.running_mean = self.momentum * self.running_mean + (1 - self.momentum) * mean
            self.running_var = self.momentum * self.running_var + (1 - self.momentum) * var
        else:
            mean = self.running_mean
            var = self.running_var

        X_norm = (X - mean) / np.sqrt(var + self.eps)
        output = self.gamma * X_norm + self.beta

        return output