keras - 与 BatchNormalization 层相关的参数数量是 2048 个？

Question

我有以下代码。

x = keras.layers.Input(batch_shape = (None, 4096))
hidden = keras.layers.Dense(512, activation = 'relu')(x)
hidden = keras.layers.BatchNormalization()(hidden)
hidden = keras.layers.Dropout(0.5)(hidden)
predictions = keras.layers.Dense(80, activation = 'sigmoid')(hidden)
mlp_model = keras.models.Model(input = [x], output = [predictions])
mlp_model.summary()

这是模型摘要:

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_3 (InputLayer)             (None, 4096)          0                                            
____________________________________________________________________________________________________
dense_1 (Dense)                  (None, 512)           2097664     input_3[0][0]                    
____________________________________________________________________________________________________
batchnormalization_1 (BatchNorma (None, 512)           2048        dense_1[0][0]                    
____________________________________________________________________________________________________
dropout_1 (Dropout)              (None, 512)           0           batchnormalization_1[0][0]       
____________________________________________________________________________________________________
dense_2 (Dense)                  (None, 80)            41040       dropout_1[0][0]                  
====================================================================================================
Total params: 2,140,752
Trainable params: 2,139,728
Non-trainable params: 1,024
____________________________________________________________________________________________________

BatchNormalization (BN) 层的输入大小为 512。根据 Keras documentation , BN 层的输出形状与输入相同，为 512。

那么BN层相关的参数个数是2048怎么办？

Answer 1

Keras 中的批量归一化实现 this paper .

正如您在那里读到的，为了在训练期间使批量归一化工作，他们需要跟踪每个归一化维度的分布。这样做，因为您在 mode=0默认情况下，他们计算上一层的每个特征 4 个参数。这些参数确保您正确传播和反向传播信息。

所以4*512 = 2048 ，这应该可以回答您的问题。