计算 Keras MLP 每个模型层的参数
Calculate the parameters per model layer for Keras MLP
我正在尝试遵循 this SO post 如何计算每一层的参数,有人可以给我提示吗?
这是我的 model.summary()
:
的输出
这是型号:
model = Sequential()
model.add(Dense(60, input_dim=44, kernel_initializer='normal', activation='relu'))
model.add(Dense(55, kernel_initializer='normal', activation='relu'))
model.add(Dense(50, kernel_initializer='normal', activation='relu'))
model.add(Dense(45, kernel_initializer='normal', activation='relu'))
model.add(Dense(30, kernel_initializer='normal', activation='relu'))
model.add(Dense(20, kernel_initializer='normal', activation='relu'))
model.add(Dense(1, kernel_initializer='normal'))
对于 MLP,等式为:
(previous_layer_nodes + 1) * (layer_nodes)
其中 +1 代表偏差。
对于输入层,上一层的节点数是input_dim
,因为输入实际上是一个。
因此,在您的情况下:
dense : (44+1)*60 = 2700
dense_1 : (60+1)*55 = 3355
dense_2 : (55+1)*50 = 2800
dense_3 : (50+1)*45 = 2295
dense_4 : (45+1)*30 = 1380
dense_5 : (30+1)*20 = 620
dense_6 : (20+1)*1 = 21
我正在尝试遵循 this SO post 如何计算每一层的参数,有人可以给我提示吗?
这是我的 model.summary()
:
这是型号:
model = Sequential()
model.add(Dense(60, input_dim=44, kernel_initializer='normal', activation='relu'))
model.add(Dense(55, kernel_initializer='normal', activation='relu'))
model.add(Dense(50, kernel_initializer='normal', activation='relu'))
model.add(Dense(45, kernel_initializer='normal', activation='relu'))
model.add(Dense(30, kernel_initializer='normal', activation='relu'))
model.add(Dense(20, kernel_initializer='normal', activation='relu'))
model.add(Dense(1, kernel_initializer='normal'))
对于 MLP,等式为:
(previous_layer_nodes + 1) * (layer_nodes)
其中 +1 代表偏差。
对于输入层,上一层的节点数是input_dim
,因为输入实际上是一个
因此,在您的情况下:
dense : (44+1)*60 = 2700
dense_1 : (60+1)*55 = 3355
dense_2 : (55+1)*50 = 2800
dense_3 : (50+1)*45 = 2295
dense_4 : (45+1)*30 = 1380
dense_5 : (30+1)*20 = 620
dense_6 : (20+1)*1 = 21