Keras函數(shù)式(functional)API的使用方式

更新時(shí)間：2023年02月22日 08:31:12 作者：黃然大悟

這篇文章主要介紹了Keras函數(shù)式(functional)API的使用方式，具有很好的參考價(jià)值，希望對大家有所幫助。如有錯誤或未考慮完全的地方，望不吝賜教

多層感知器(Multilayer Perceptron)
卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Network)
循環(huán)神經(jīng)網(wǎng)絡(luò)(Recurrent Neural Network)
Bidirectional recurrent neural network
共享輸入層模型(Shared Input Layer Model)
Shared Feature Extraction Layer
多輸入模型(Multiple Input Model)
多輸出模型(Multiple Output Model)
總結(jié)

多層感知器(Multilayer Perceptron)

定義了用于二分類的多層感知器模型。

模型輸入32維特征，經(jīng)過三個(gè)全連接層，每層使用relu線性激活函數(shù)，并且在輸出層中使用sigmoid激活函數(shù)，最后用于二分類。

##------ Multilayer Perceptron ------##
from keras.models import Model
from keras.layers import Input, Dense
from keras import backend as K
K.clear_session() 

# MLP model
x = Input(shape=(32,))
hidden1 = Dense(10, activation='relu')(x)
hidden2 = Dense(20, activation='relu')(hidden1)
hidden3 = Dense(10, activation='relu')(hidden2)
output = Dense(1, activation='sigmoid')(hidden3)
model = Model(inputs=x, outputs=output)

# summarize layers
model.summary()

模型的結(jié)構(gòu)和參數(shù)如下：

Multilayer Perceptron

卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Network)

定義用于圖像分類的卷積神經(jīng)網(wǎng)絡(luò)。

該模型接收3通道的64×64圖像作為輸入，然后經(jīng)過兩個(gè)卷積和池化層的序列作為特征提取器，接著過一個(gè)全連接層，最后輸出層過softmax激活函數(shù)進(jìn)行10個(gè)類別的分類。

##------ Convolutional Neural Network ------##
from keras.models import Model
from keras.layers import Input
from keras.layers import Dense, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
K.clear_session()

# CNN model
x = Input(shape=(64,64,3))
conv1 = Conv2D(16, (5,5), activation='relu')(x)
pool1 = MaxPooling2D((2,2))(conv1)
conv2 = Conv2D(32, (3,3), activation='relu')(pool1)
pool2 = MaxPooling2D((2,2))(conv2)
conv3 = Conv2D(32, (3,3), activation='relu')(pool2)
pool3 = MaxPooling2D((2,2))(conv3)
flat = Flatten()(pool3)
hidden1 = Dense(512, activation='relu')(flat)
output = Dense(10, activation='softmax')(hidden1)
model = Model(inputs=x, outputs=output)

# summarize layers
model.summary()

模型的結(jié)構(gòu)和參數(shù)如下：

CNN

循環(huán)神經(jīng)網(wǎng)絡(luò)(Recurrent Neural Network)

定義一個(gè)用于文本序列分類的LSTM網(wǎng)絡(luò)。

該模型需要100個(gè)時(shí)間步長作為輸入，然后經(jīng)過一個(gè)Embedding層，每個(gè)時(shí)間步變成128維特征表示，然后經(jīng)過一個(gè)LSTM層，LSTM輸出過一個(gè)全連接層，最后輸出用sigmoid激活函數(shù)用于進(jìn)行二分類預(yù)測。

##------ Recurrent Neural Network ------##
from keras.models import Model
from keras.layers import Input
from keras.layers import Dense, LSTM, Embedding
from keras import backend as K
K.clear_session()

VOCAB_SIZE = 10000
EMBED_DIM = 128

x = Input(shape=(100,), dtype='int32')
embedding = Embedding(VOCAB_SIZE, EMBED_DIM, mask_zero=True)(x)
hidden1 = LSTM(64)(embedding)
hidden2 = Dense(32, activation='relu')(hidden1)
output = Dense(1, activation='sigmoid')(hidden2)
model = Model(inputs=x, outputs=output)

# summarize layers
model.summary()

模型的結(jié)構(gòu)和參數(shù)如下：

LSTM

Bidirectional recurrent neural network

定義一個(gè)雙向循環(huán)神經(jīng)網(wǎng)絡(luò)，可以用來完成序列標(biāo)注等任務(wù)，相比上面的LSTM網(wǎng)絡(luò)，多了一個(gè)反向的LSTM，其它設(shè)置一樣。

##------ Bidirectional recurrent neural network ------##
from keras.models import Model
from keras.layers import Input, Embedding
from keras.layers import Dense, LSTM, Bidirectional
from keras import backend as K
K.clear_session()

VOCAB_SIZE = 10000
EMBED_DIM = 128
HIDDEN_SIZE = 64
# input layer
x = Input(shape=(100,), dtype='int32')
# embedding layer
embedding = Embedding(VOCAB_SIZE, EMBED_DIM, mask_zero=True)(x)
# BiLSTM layer
hidden = Bidirectional(LSTM(HIDDEN_SIZE, return_sequences=True))(embedding)
# prediction layer
output = Dense(10, activation='softmax')(hidden)
model = Model(inputs=x, outputs=output)

model.summary()

模型的結(jié)構(gòu)和參數(shù)如下：

BiLSTM

共享輸入層模型(Shared Input Layer Model)

定義了具有不同大小內(nèi)核的多個(gè)卷積層來解釋圖像輸入。

該模型采用尺寸為64×64像素的3通道圖像。

有兩個(gè)共享此輸入的CNN特征提取子模型; 第一個(gè)內(nèi)核大小為5x5，第二個(gè)內(nèi)核大小為3x3。

把提取的特征展平為向量然后拼接成一個(gè)長向量，然后過一個(gè)全連接層，最后輸出層完成10分類。

##------ Shared Input Layer Model ------##

from keras.models import Model
from keras.layers import Input
from keras.layers import Dense, Flatten
from keras.layers import Conv2D, MaxPooling2D, Concatenate
from keras import backend as K
K.clear_session()

# input layer
x = Input(shape=(64,64,3))
# first feature extractor
conv1 = Conv2D(32, (3,3), activation='relu')(x)
pool1 = MaxPooling2D((2,2))(conv1)
flat1 = Flatten()(pool1)
# second feature extractor 
conv2 = Conv2D(16, (5,5), activation='relu')(x)
pool2 = MaxPooling2D((2,2))(conv2)
flat2 = Flatten()(pool2)
# merge feature
merge = Concatenate()([flat1, flat2])
# interpretation layer
hidden1 = Dense(128, activation='relu')(merge)
# prediction layer
output = Dense(10, activation='softmax')(merge)
model = Model(inputs=x, outputs=output)

model.summary()

模型的結(jié)構(gòu)和參數(shù)如下：

Shared-Input-Layer

Shared Feature Extraction Layer

定義一個(gè)共享特征抽取層的模型，這里共享的是LSTM層的輸出，具體共享參見代碼

##------ Shared Feature Extraction Layer ------##
from keras.models import Model
from keras.layers import Input, Embedding
from keras.layers import Dense, LSTM, Concatenate
from keras import backend as K
K.clear_session()

# input layer
x = Input(shape=(100,32))
# feature extraction
extract1 = LSTM(64)(x)
# first interpretation model
interp1 = Dense(32, activation='relu')(extract1)
# second interpretation model
interp11 = Dense(64, activation='relu')(extract1)
interp12 = Dense(32, activation='relu')(interp11)
# merge interpretation
merge = Concatenate()([interp1, interp12])
# output layer
output = Dense(10, activation='softmax')(merge)
model = Model(inputs=x, outputs=output)

model.summary()

模型的結(jié)構(gòu)和參數(shù)如下：

Shared-Feature-Extraction-Layer

多輸入模型(Multiple Input Model)

定義有兩個(gè)輸入的模型，這里測試的是輸入兩張圖片，一個(gè)輸入是單通道的64x64，另一個(gè)是3通道的32x32，兩個(gè)經(jīng)過卷積層、池化層后，展平拼接，最后進(jìn)行二分類。

##------ Multiple Input Model  ------##
from keras.models import Model
from keras.layers import Input
from keras.layers import Dense, Flatten
from keras.layers import Conv2D, MaxPooling2D, Concatenate
from keras import backend as K
K.clear_session()

# first input model
input1 = Input(shape=(64,64,1))
conv11 = Conv2D(32, (5,5), activation='relu')(input1)
pool11 = MaxPooling2D(pool_size=(2,2))(conv11)
conv12 = Conv2D(16, (3,3), activation='relu')(pool11)
pool12 = MaxPooling2D(pool_size=(2,2))(conv12)
flat1 = Flatten()(pool12)
# second input model
input2 = Input(shape=(32,32,3))
conv21 = Conv2D(32, (5,5), activation='relu')(input2)
pool21 = MaxPooling2D(pool_size=(2,2))(conv21)
conv22 = Conv2D(16, (3,3), activation='relu')(pool21)
pool22 = MaxPooling2D(pool_size=(2,2))(conv22)
flat2 = Flatten()(pool22)
# merge input models
merge = Concatenate()([flat1, flat2])
# interpretation model
hidden1 = Dense(20, activation='relu')(merge)
output = Dense(1, activation='sigmoid')(hidden1)
model = Model(inputs=[input1, input2], outputs=output)

model.summary()

模型的結(jié)構(gòu)和參數(shù)如下：

Multiple-Input-Model

多輸出模型(Multiple Output Model)

定義有多個(gè)輸出的模型，以文本序列輸入LSTM網(wǎng)絡(luò)為例，一個(gè)輸出是對文本的分類，另外一個(gè)輸出是對文本進(jìn)行序列標(biāo)注。

##------ Multiple Output Model ------ ##
from keras.models import Model
from keras.layers import Input
from keras.layers import Dense, Flatten, TimeDistributed, LSTM
from keras.layers import Conv2D, MaxPooling2D, Concatenate
from keras import backend as K
K.clear_session()

x = Input(shape=(100,1))
extract = LSTM(10, return_sequences=True)(x)

class11 = LSTM(10)(extract)
class12 = Dense(10, activation='relu')(class11)
output1 = Dense(1, activation='sigmoid')(class12)
output2 = TimeDistributed(Dense(1, activation='linear'))(extract)
model = Model(inputs=x, outputs=[output1, output2])

model.summary()

模型的結(jié)構(gòu)和參數(shù)如下：

Multiple-Output-Model