Question

谁能为我推荐解决此类错误的最佳途径？我无法弄清楚尺寸方面做错了什么。我有一个源于Word2Vec gensim模型的预训练嵌入，我想使用该模型来初始化CNN。抱歉，这个问题相对简单，但对于Keras和Tensorflow来说都是新事物

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>ch.uzh.ifi.csg.cloudsim</groupId>
    <artifactId>rda</artifactId>
    <version>1.0</version>
    <packaging>jar</packaging>

    <name>Cloudsim RDA (Resource Dependency Aware)</name>
    <url>https://github.com/pattad/cloudsim-rda</url>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.1</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.cloudbus.cloudsim</groupId>
            <artifactId>cloudsim</artifactId>
            <version>3.1-SNAPSHOT</version>
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-math3</artifactId>
            <version>3.3</version>
        </dependency>
    </dependencies>
    <description>This module enhances the cloud simulator project cloudsim (see http://www.cloudbus.org/cloudsim) with resource dependency aware workloads.</description>
</project>

输出为：

#CNN architecture

num_classes = num_labels

#Training params
batch_size = 8 
num_epochs = 25

#Model parameters
num_filters = 64  
weight_decay = 1e-4
kernel_size = 7 #this is the size of the window during convolution...making match the window size in Word2Vec...unsure if needed

print("training CNN ...")

model = Sequential()

#------------------------
FIXED_LENGTH=embedding_matrix.shape[1]
#------------------------

print('Vocab size:', vocab_size)
print('Output_Dim size:', w2v.vector_size)
print('Weights:', pd.Series([embedding_matrix]).shape)
print('Weights underlying shape:', embedding_matrix.shape)
print("Input Length:", FIXED_LENGTH)

#Model add word2vec embedding

model.add(Embedding(vocab_size+1, 
                      output_dim=w2v.vector_size, 
                      weights=[embedding_matrix], 
                      input_length=FIXED_LENGTH, 
                      trainable=False))
model.add(Conv1D(num_filters, kernel_size=kernel_size, activation='relu', padding='same'))
model.add(MaxPooling1D(2))
model.add(Conv1D(num_filters, 7, activation='relu', padding='same'))
model.add(GlobalMaxPooling1D())
model.add(Dropout(0.5))
model.add(Dense(32, activation='relu', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Dense(num_classes, activation='softmax'))  #multi-label (k-hot encoding)

adam = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
model.compile(loss='sparse_categorical_crossentropy', optimizer=adam, metrics=['accuracy'])
model.summary()

#define callbacks
early_stopping = EarlyStopping(monitor='val_loss', min_delta=0.01, patience=4, verbose=1)
callbacks_list = [early_stopping]

print('Batch size:', batch_size)
print('Num of Epochs:', num_epochs)
print('X Train Size:', x_train_pad.shape)
print('Y Train Size:', y_train.shape)

hist = model.fit(x_train_pad, 
                 y_train, 
                 batch_size=batch_size, 
                 epochs=num_epochs, 
                 callbacks=callbacks_list, 
                 validation_split=0.1, 
                 shuffle=True, 
                 verbose=2)

Answer 1

可以将嵌入层中的vocab_size+1参数更改为vocab_size。我认为是造成问题的+1

Answer 2

答案是编码的句子包含的值比词典构建阶段中编码的值高。在您的词典中，应该为您的培训和测试集的每个值提供一个索引。如果没有，则必须先清理句子，然后再将其发送到CNN。

Tensorflow Keras嵌入层错误：层权重形状不兼容

2 个答案: