Question

我正在使用Keras开发LSTM-RNN文本分类这是我的代码。

import numpy as np
import csv
import keras
import sklearn
import gensim
import random
import scipy
from keras.preprocessing import text
from keras.preprocessing import sequence
from keras.preprocessing.text import Tokenizer
from keras.models import Sequential
from keras.layers.core import Dense , Dropout , Activation  , Flatten
from keras.layers.convolutional import Convolution1D, MaxPooling1D
from keras.layers import Embedding , LSTM
from sklearn import preprocessing
from sklearn.base import BaseEstimator
from sklearn.svm import LinearSVC , SVC
from sklearn.naive_bayes import MultinomialNB
from gensim.models.word2vec import Word2Vec
from gensim.models.doc2vec import Doc2Vec , TaggedDocument

# size of the word embeddings
embeddings_dim = 300

# maximum number of words to consider in the representations
max_features = 30000

# maximum length of a sentence
max_sent_len = 50

# percentage of the data used for model training
percent = 0.75

# number of classes
num_classes = 2

print ("")
print ("Reading pre-trained word embeddings...")
embeddings = dict( )
embeddings = gensim.models.KeyedVectors.load_word2vec_format("GoogleNews-vectors-negative300.bin.gz" , binary=True) 

print ("Reading text data for classification and building representations...")
data = [ ( row["sentence"] , row["label"]  ) for row in csv.DictReader(open("test-data.txt"), delimiter='\t', quoting=csv.QUOTE_NONE) ]
random.shuffle( data )
train_size = int(len(data) * percent)
train_texts = [ txt.lower() for ( txt, label ) in data[0:train_size] ]
test_texts = [ txt.lower() for ( txt, label ) in data[train_size:-1] ]
train_labels = [ label for ( txt , label ) in data[0:train_size] ]
test_labels = [ label for ( txt , label ) in data[train_size:-1] ]
num_classes = len( set( train_labels + test_labels ) )
tokenizer = Tokenizer(num_words=max_features, filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n', lower=True, split=" ")
tokenizer.fit_on_texts(train_texts)
train_sequences = sequence.pad_sequences( tokenizer.texts_to_sequences( train_texts ) , maxlen=max_sent_len )
test_sequences = sequence.pad_sequences( tokenizer.texts_to_sequences( test_texts ) , maxlen=max_sent_len )
train_matrix = tokenizer.texts_to_matrix( train_texts )
test_matrix = tokenizer.texts_to_matrix( test_texts )
embedding_weights = np.zeros( ( max_features , embeddings_dim ) )
for word,index in tokenizer.word_index.items():
  if index < max_features:
    try: embedding_weights[index,:] = embeddings[word]
    except: embedding_weights[index,:] = np.random.rand( 1 , embeddings_dim )
le = preprocessing.LabelEncoder( )
le.fit( train_labels + test_labels )
train_labels = le.transform( train_labels )
test_labels = le.transform( test_labels )
print("Classes that are considered in the problem : " + repr( le.classes_ ))


print("-----WEIGHTS-----")
print(embedding_weights.shape)

print ("Method = Stack of two LSTMs")
np.random.seed(0)
model = Sequential()

model.add(Embedding(max_features, embeddings_dim, input_length=max_sent_len, mask_zero=True, weights=[embedding_weights] ))
model.add(Dropout(0.25))
model.add(LSTM(output_dim=embeddings_dim , activation='sigmoid', inner_activation='hard_sigmoid', return_sequences=True))
model.add(Dropout(0.25))
model.add(LSTM(activation="sigmoid", units=embeddings_dim, recurrent_activation="hard_sigmoid", return_sequences=True))
model.add(Dropout(0.25))
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy', optimizer='adam', class_mode='binary')
else: model.compile(Adam(lr=0.04),'categorical_crossentropy',metrics=['accuracy'])

model.summary()


model.fit(train_sequences, train_labels , epochs=30, batch_size=32)

我的模特是这个

Layer (type)                 Output Shape              Param #   
=================================================================
embedding_1 (Embedding)      (None, 50, 300)           9000000   
_________________________________________________________________
dropout_1 (Dropout)          (None, 50, 300)           0         
_________________________________________________________________
lstm_1 (LSTM)                (None, 50, 300)           721200    
_________________________________________________________________
dropout_2 (Dropout)          (None, 50, 300)           0         
_________________________________________________________________
lstm_2 (LSTM)                (None, 50, 300)           721200    
_________________________________________________________________
dropout_3 (Dropout)          (None, 50, 300)           0         
_________________________________________________________________
dense_1 (Dense)              (None, 50, 1)             301       
_________________________________________________________________
activation_1 (Activation)    (None, 50, 1)             0         
=================================================================
Total params: 10,442,701
Trainable params: 10,442,701
Non-trainable params: 0

我的错误是：检查目标时出错：预期的activation_1的维度为3，但数组的形状为（750，1）

我尝试重塑所有数组，但找不到解决方案。有人能帮我吗？？？谢谢你：D 对不起，我的英语不好。

Answer 1

您需要对标签进行热编码。您可以使用Keras to_categorical方法转换标签编码的整数。

Answer 2

最后，我的模型是

model = Sequential()

model.add(Embedding(max_features, embeddings_dim, input_length=max_sent_len, mask_zero=True, weights=[embedding_weights] ))
model.add(Dropout(0.25))
model.add(LSTM(output_dim=embeddings_dim , activation='sigmoid', inner_activation='hard_sigmoid', return_sequences=True))
model.add(Dropout(0.25))
model.add(LSTM(activation='sigmoid', units=embeddings_dim, recurrent_activation='hard_sigmoid', return_sequences=False))
model.add(Dropout(0.25))
model.add(Dense(num_classes))
model.add(Activation('sigmoid'))

adam=keras.optimizers.Adam(lr=0.04)
model.compile(optimizer=adam, loss='categorical_crossentropy', metrics=['accuracy'])

但是准确性非常差！！！ :(

文本分类RNN-LSTM-错误检查目标

2 个答案: