class Scale(Layer):
    def __init__(self, weights=None, axis=-1, momentum = 0.9, beta_init='zero', gamma_init='one', **kwargs):
        self.momentum = momentum
        self.axis = axis
        self.beta_init = initializations.get(beta_init)
        self.gamma_init = initializations.get(gamma_init)
        self.initial_weights = weights
        super(Scale, self).__init__(**kwargs)
    def build(self, input_shape):
        self.input_spec = [InputSpec(shape=input_shape)]
        shape = (int(input_shape[self.axis]),)
        # Tensorflow >= 1.0.0 compatibility
        self.gamma = K.variable(self.gamma_init(shape), name='{}_gamma'.format(self.name))
        self.beta = K.variable(self.beta_init(shape), name='{}_beta'.format(self.name))
        #self.gamma = self.gamma_init(shape, name='{}_gamma'.format(self.name))
        #self.beta = self.beta_init(shape, name='{}_beta'.format(self.name))
        self.trainable_weights = [self.gamma, self.beta]

        if self.initial_weights is not None:
            self.set_weights(self.initial_weights)
            del self.initial_weights

    def call(self, x, mask=None):
        input_shape = self.input_spec[0].shape
        broadcast_shape = [1] * len(input_shape)
        broadcast_shape[self.axis] = input_shape[self.axis]

        out = K.reshape(self.gamma, broadcast_shape) * x + K.reshape(self.beta, broadcast_shape)
        return out

    def get_config(self):
        config = {"momentum": self.momentum, "axis": self.axis}
        base_config = super(Scale, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))
 

終於把這個程式碼看懂了一點點。。

主要是呼叫的時候主要是def call

基本意思是對接受上一層的輸出比如是（12,12,64）的變數x，對其處理是用（1,1,64）的f變數乘以x,再加上（1,1,64）的偏量d。基本上公式是fx+d,剛開始不知道怎麼理解這個三維的陣列相乘，實際是這樣的64個12X12的矩陣與64個1x1的常量相乘，再加上64個1x1的常量，最後就得到最後的x.

又看了幾個名詞把banach代數，對偶空間，零化子c*代數就是滿足不同的運算封閉性。。