Question

我遇到一个错误：

Error when checking input: 
expected embedding_1_input to have shape (50,) but got array with shape (1,)

当我将输入参数input_length更改为1时，错误变为：

Error when checking input: 
expected embedding_1_input to have shape (1,) but got array with shape (50,)

我的代码如下：

from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer, TfidfVectorizer
import numpy as np
import os
from keras import metrics
from keras.layers import Dense, Dropout, Embedding, LSTM, Bidirectional, BatchNormalization, Activation, Conv1D, MaxPooling1D, Flatten, GlobalMaxPooling1D
from keras.models import load_model
from keras.callbacks import ModelCheckpoint
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.preprocessing import sequence, text
import pandas as pd
from gensim import corpora
from gensim import models

maxlen = 50
batch_size = 128
np.random.seed(7)

df = pd.read_csv('C:/Users/DMY/Peer-logic-master/newdata/topnine.csv',encoding='utf-8')

x = df["REVIEW"].fillna("na").values  
y = df["TAG"]
encoder = LabelEncoder()
encoder.fit(y)
y = encoder.transform(y)

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.1)

word_list = []

for i in range(len(x_train)):
    word_list.append(x_train[i].split(' '))


dictionary = corpora.Dictionary(word_list)
corpus = [dictionary.doc2bow(text) for text in word_list]


tfidf = models.TfidfModel(corpus)

X_train_id = [] 
word_id_dict = dictionary.token2id
for i in range(len(word_list)):
    sen_id = []
    word_sen = word_list[i]
    for j in range(len(word_sen)):       
        id = word_id_dict.get(word_sen[j])
        if id is None:
            id = 0 
        sen_id.append(id)
    X_train_id.append(sen_id)

X_train_tfidf_vec = []  
for i in range(len(x_train)):
    temp = {}
    string = x_train[i]
    string_bow = dictionary.doc2bow(string.lower().split()) 
    string_tfidf = tfidf[string_bow]

    for j in range(len(string_tfidf)):
#         print(string_tfidf[j][0])
        temp[string_tfidf[j][0]] = string_tfidf[j][1]
#         print(temp)
    X_train_tfidf_vec.append(temp)

X_train_tfidf = []  
for i in range(len(X_train_id)):
    sen_id = X_train_id[i]
    sen_id_tfidf = X_train_tfidf_vec[i]
    sen = []
    for j in range(len(sen_id)):
        word_id = sen_id[j]
        word_tfidf = sen_id_tfidf.get(word_id)
        if word_tfidf is None:
            word_tfidf = 0
        sen.append(word_tfidf)
    X_train_tfidf.append(sen)

x_train_tfidf = sequence.pad_sequences(X_train_tfidf, maxlen=maxlen,dtype='float64')
#print(len(x_train_tfidf))
#print(x_train_tfidf)

model4 = Sequential()
model4.add(Embedding(len(x_train_tfidf)+1, 100, input_length = ))#input_dim,output_dim,input_length
model4.add(Dropout(0.6))
model4.add(LSTM(100, recurrent_dropout=0.6))
model4.add(Dropout(0.6))
model4.add(Dense(1, activation='sigmoid'))
model4.compile('adam', 'binary_crossentropy', metrics=['accuracy'])
model4_history = model4.fit(x_train_tfidf, y_train, batch_size=batch_size, epochs=7,
                            validation_split=0.1)
score4, acc4 = model4.evaluate(x_test, y_test,
                               batch_size=batch_size)
print('Test accuracy for LSTM Model is:', acc4)
y_pred4 = model4.predict(x_test)
y_pred4 = (y_pred4 > 0.5)
print(classification_report(y_test, y_pred4))

Answer 1

根据official documentation，嵌入层采用许多不同的初始化参数。

Embedding(input_dim, 
          output_dim, 
          embeddings_initializer='uniform', 
          embeddings_regularizer=None, 
          activity_regularizer=None, 
          embeddings_constraint=None, 
          mask_zero=False, 
          input_length=None)

请注意，input_dim指定输入数据的词汇量，即即。数据中有多少个不同的单词。 output_dim指定潜在空间的维度，即即。在嵌入转换后，每个单词的向量将持续多长时间。

让我们用一个例子来说明这一点。考虑以下层：

model.add(Embedding(1000, 64, input_length=10))

这表明以下事实

数据中有1000个唯一的单词
每个单词将被表示为64维向量
数据中的实例将是10个单词的短语

此层的输出将为(None, 10, 64)形状，其中None是批处理大小。在您的情况下，input_length应该设置为等于maxlen，这似乎指定了输入数据中每个实例的大小。

检查输入时出错：预期embedding_1_input具有形状（50，），但数组的形状为（1，）

1 个答案: