tensorflow2.x学习笔记五：构建模型的三种方式
前言
可以使用以下3种方式构建模型：
- 使用Sequential按层顺序构建模型，
- 使用函数式API构建任意结构模型，
- 继承Model基类构建自定义模型。
对于顺序结构的模型，优先使用Sequential方法构建。
如果模型有多输入或者多输出，或者模型需要共享权重，或者模型具有残差连接等非顺序结构，推荐使用函数式API进行创建。
如果无特定必要，尽可能避免使用Model子类化的方式构建模型，这种方式提供了极大的灵活性，但也有更大的概率出错。
一，Sequential按层顺序创建模型
tf.keras.backend.clear_session()
model = models.Sequential()
model.add(layers.Embedding(MAX_WORDS,7,input_length=MAX_LEN))
model.add(layers.Conv1D(filters = 64,kernel_size = 5,activation = "relu"))
model.add(layers.MaxPool1D(2))
model.add(layers.Conv1D(filters = 32,kernel_size = 3,activation = "relu"))
model.add(layers.MaxPool1D(2))
model.add(layers.Flatten())
model.add(layers.Dense(1,activation = "sigmoid"))
model.compile(optimizer='Nadam',
loss='binary_crossentropy',
metrics=['accuracy',"AUC"])
model.summary()
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding (Embedding) (None, 200, 7) 70000
_________________________________________________________________
conv1d (Conv1D) (None, 196, 64) 2304
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 98, 64) 0
_________________________________________________________________
conv1d_1 (Conv1D) (None, 96, 32) 6176
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 48, 32) 0
_________________________________________________________________
flatten (Flatten) (None, 1536) 0
_________________________________________________________________
dense (Dense) (None, 1) 1537
=================================================================
Total params: 80,017
Trainable params: 80,017
Non-trainable params: 0
二，函数式API创建任意结构模型
tf.keras.backend.clear_session()
inputs = layers.Input(shape=(200,))
x = layers.Embedding(MAX_WORDS,7)(inputs)
branch1 = layers.SeparableConv1D(64,3,activation="relu")(x)
branch1 = layers.MaxPool1D(3)(branch1)
branch1 = layers.SeparableConv1D(32,3,activation="relu")(branch1)
branch1 = layers.GlobalMaxPool1D()(branch1)
branch2 = layers.SeparableConv1D(64,5,activation="relu")(x)
branch2 = layers.MaxPool1D(5)(branch2)
branch2 = layers.SeparableConv1D(32,5,activation="relu")(branch2)
branch2 = layers.GlobalMaxPool1D()(branch2)
branch3 = layers.SeparableConv1D(64,7,activation="relu")(x)
branch3 = layers.MaxPool1D(7)(branch3)
branch3 = layers.SeparableConv1D(32,7,activation="relu")(branch3)
branch3 = layers.GlobalMaxPool1D()(branch3)
concat = layers.Concatenate()([branch1,branch2,branch3])
outputs = layers.Dense(1,activation = "sigmoid")(concat)
model = models.Model(inputs = inputs,outputs = outputs)
model.compile(optimizer='Nadam',
loss='binary_crossentropy',
metrics=['accuracy',"AUC"])
model.summary()
Model: "model"
________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
========================================================================================
input_1 (InputLayer) [(None, 200)] 0
________________________________________________________________________________________
embedding (Embedding) (None, 200, 7) 70000 input_1[0][0]
________________________________________________________________________________________
separable_conv1d (SeparableConv (None, 198, 64) 533 embedding[0][0]
________________________________________________________________________________________
separable_conv1d_2 (SeparableCo (None, 196, 64) 547 embedding[0][0]
________________________________________________________________________________________
separable_conv1d_4 (SeparableCo (None, 194, 64) 561 embedding[0][0]
________________________________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 66, 64) 0 separable_conv1d[0][0]
________________________________________________________________________________________
max_pooling1d_1 (MaxPooling1D) (None, 39, 64) 0 separable_conv1d_2[0][0]
________________________________________________________________________________________
max_pooling1d_2 (MaxPooling1D) (None, 27, 64) 0 separable_conv1d_4[0][0]
________________________________________________________________________________________
separable_conv1d_1 (SeparableCo (None, 64, 32) 2272 max_pooling1d[0][0]
________________________________________________________________________________________
separable_conv1d_3 (SeparableCo (None, 35, 32) 2400 max_pooling1d_1[0][0]
________________________________________________________________________________________
separable_conv1d_5 (SeparableCo (None, 21, 32) 2528 max_pooling1d_2[0][0]
________________________________________________________________________________________
global_max_pooling1d (GlobalMax (None, 32) 0 separable_conv1d_1[0][0]
________________________________________________________________________________________
global_max_pooling1d_1 (GlobalM (None, 32) 0 separable_conv1d_3[0][0]
________________________________________________________________________________________
global_max_pooling1d_2 (GlobalM (None, 32) 0 separable_conv1d_5[0][0]
________________________________________________________________________________________
concatenate (Concatenate) (None, 96) 0 global_max_pooling1d[0][0]
global_max_pooling1d_1[0][0]
global_max_pooling1d_2[0][0]
________________________________________________________________________________________
dense (Dense) (None, 1) 97 concatenate[0][0]
========================================================================================
Total params: 78,938
Trainable params: 78,938
Non-trainable params: 0
三，继承Model类创建自定义模型
# 先自定义一个残差模块，为自定义Layer
class ResBlock(layers.Layer):
def __init__(self, kernel_size, **kwargs):
super(ResBlock, self).__init__(**kwargs)
self.kernel_size = kernel_size
def build(self,input_shape):
self.conv1 = layers.Conv1D(filters=64,kernel_size=self.kernel_size,
activation = "relu",padding="same")
self.conv2 = layers.Conv1D(filters=32,kernel_size=self.kernel_size,
activation = "relu",padding="same")
self.conv3 = layers.Conv1D(filters=input_shape[-1],
kernel_size=self.kernel_size,
activation = "relu",padding="same")
self.maxpool = layers.MaxPool1D(2)
super(ResBlock,self).build(input_shape) # 相当于设置self.built = True
def call(self, inputs):
x = self.conv1(inputs)
x = self.conv2(x)
x = self.conv3(x)
x = layers.Add()([inputs,x])
x = self.maxpool(x)
return x
class ImdbModel(models.Model):
def __init__(self):
super(ImdbModel, self).__init__()
def build(self,input_shape):
self.embedding = layers.Embedding(MAX_WORDS,7)
self.block1 = ResBlock(7)
self.block2 = ResBlock(5)
self.dense = layers.Dense(1,activation = "sigmoid")
super(ImdbModel,self).build(input_shape)
def call(self, x):
x = self.embedding(x)
x = self.block1(x)
x = self.block2(x)
x = layers.Flatten()(x)
x = self.dense(x)
return(x)
tf.keras.backend.clear_session()
model = ImdbModel()
model.build(input_shape =(None,200))
model.compile(optimizer='Nadam',
loss='binary_crossentropy',
metrics=['accuracy',"AUC"])
model.summary()
Model: "imdb_model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding (Embedding) multiple 70000
_________________________________________________________________
res_block (ResBlock) multiple 19143
_________________________________________________________________
res_block_1 (ResBlock) multiple 13703
_________________________________________________________________
dense (Dense) multiple 351
=================================================================
Total params: 103,197
Trainable params: 103,197
Non-trainable params: 0
参考链接：eat_tensorflow2_in_30_days