if self.samplewise_center:
            x -= np.mean(x, keepdims=True)  #減去每個批次feature的平均值實現0中心化
        if self.samplewise_std_normalization:
            x /= (np.std(x, keepdims=True) + K.epsilon())  #除以每個批次feature的標準差
        if self.featurewise_center:
            self.mean = np.mean(x, axis=(0, self.row_axis, self.col_axis))  #在底層為tendorflow時這裡#self.row_axis=1，self.col_axis=2,即axis(0,1,2)。因為x是一個4維np,最後一維即影象的通道數，所
#以這裡計算機的每一通道的畫素平均值。
            broadcast_shape = [1, 1, 1]
            broadcast_shape[self.channel_axis - 1] = x.shape[self.channel_axis]
            self.mean = np.reshape(self.mean, broadcast_shape)  #對應mean的shape
            x -= self.mean    #對每批次的資料減對應通道畫素的均值

        if self.featurewise_std_normalization:
            self.std = np.std(x, axis=(0, self.row_axis, self.col_axis))
            broadcast_shape = [1, 1, 1]
            broadcast_shape[self.channel_axis - 1] = x.shape[self.channel_axis]
            self.std = np.reshape(self.std, broadcast_shape)
            x /= (self.std + K.epsilon())  #對每批次的資料除以對應通道畫素的標準差
 

ImageDataGenerator(
        featurewise_center=True,  #均值為0
        featurewise_std_normalization=True,#標準化處理
        samplewise_center=False,
        samplewise_std_normalization=False,
        )