检查输入时出错：预期 embedding_1_input 的形状为 (4,) 但数组的形状为 (1,)

Question

我为我的 keras 模型使用预训练的嵌入向量。在我这样做之前一切正常，现在我得到了这个错误：

ValueError：检查输入时出错：预期 embedding_1_input 到 有形状 (4,) 但得到了形状 (1,) 的数组

也许有人可以帮助我，我在这里做错了什么。我不确定我是否正确地使用了 model.fit 和 model.evaluate。可能有问题？

import csv
import numpy as np
np.random.seed(42)
from keras.models import Sequential, Model
from keras.layers import *
from random import shuffle
from sklearn.model_selection import train_test_split
from keras import optimizers
from keras.callbacks import EarlyStopping
from itertools import groupby
from numpy import asarray
from numpy import zeros 
from numpy import array
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences

#function makes a list of antonyms and synonyms from the files
def preprocessing(filename):
    list_words = []
    with open(filename) as tsv:
       for line in csv.reader(tsv, dialect="excel-tab"):
           list_words.append([line[0], line[1]])
    return list_words

#function make a list of not relevant pairs by mixing synonyms and 
antonyms
def notrelevant(filename, filename2):
    list_words = []
    with open(filename) as tsv:
        with open(filename2) as tsv2:
           for lines in zip(csv.reader(tsv, dialect="excel-tab"),csv.reader(tsv2, dialect="excel-tab")):
                list_words.append([lines[0][0], lines[1][1]])
    return list_words

antonyms_list = preprocessing("antonyms.tsv")
synonyms_list = preprocessing("synonyms.tsv")
notrelevant_list = notrelevant("antonyms.tsv", "synonyms.tsv")

# function combines all antonyms, synonyms in one list with labels, 
shuffle them
def data_prepare(ant,syn,nrel):
        data = []
    for  elem1,elem2 in ant:
        data.append([[elem1,elem2], "Antonyms"])
    for elem1, elem2 in syn:
        data.append([[elem1, elem2], "Synonyms"])
    for elem1, elem2 in nrel:
        data.append([[elem1, elem2], "Not relevant"])
    shuffle(data)
    return data


data_with_labels_shuffled = 
data_prepare(antonyms_list,synonyms_list,notrelevant_list)

def label_to_onehot(labels):
    mapping = {label: i for i, label in enumerate(set(labels))}

    one_hot = np.empty((len(labels), 3))
    for i, label in enumerate(labels):
        entry = [0] * len(mapping)
        entry[mapping[label]] = 1
        one_hot[i] = entry
    return (one_hot)

def words_to_ids(labels):
    vocabulary = []
    word_to_id = {}
    ids = []
    for word1,word2 in labels:
        vocabulary.append(word1)
        vocabulary.append(word2)
    counter = 0
    for word in vocabulary:
        if word not in word_to_id:
            word_to_id[word] = counter
            counter += 1
    for word1,word2 in labels:
        ids.append([word_to_id [word1], word_to_id [word2]])
    return (ids)

def split_data(datas):
    data = np.array(datas)
    X, y = data[:, 0], data[:, 1]
    # split the data to get 60% train and 40% test
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=42)
    y_train = label_to_onehot(y_train)
    X_dev, X_test, y_dev, y_test = train_test_split(X_test, y_test, test_size=0.5, random_state=42)
    y_dev = label_to_onehot(y_dev)
    y_test = label_to_onehot(y_test)
    return X_train, y_train, X_dev, y_dev, X_test, y_test

X_train, y_train, X_dev, y_dev, X_test, y_test = split_data(data_with_labels_shuffled)

# prepare tokenizer
t = Tokenizer()
t.fit_on_texts(X_train)
vocab_size = len(t.word_index) + 1
# integer encode the documents
encoded_docs = t.texts_to_sequences(X_train)


# load the whole embedding into memory
embeddings_index = dict()
f = open('glove.6B.50d.txt')
for line in f:
    values = line.split()
    word = values[0]
    coefs = asarray(values[1:], dtype='float32')
    embeddings_index[word] = coefs
f.close()
# create a weight matrix for words in training docs
embedding_matrix = zeros((vocab_size, 50))
for word, i in t.word_index.items():
    embedding_vector = embeddings_index.get(word)
    if embedding_vector is not None:
        embedding_matrix[i] = embedding_vector



VOCABSIZE = len(data_with_labels_shuffled)
EMBSIZE = 50
HIDDENSIZE = 50
KERNELSIZE = 5
MAXEPOCHS = 5

model = Sequential()
model.add(Embedding(vocab_size, 50, weights=[embedding_matrix], 
input_length=4, trainable=False))
model.add(Dropout(0.25))
model.add(Bidirectional(GRU(units = HIDDENSIZE // 2)))
#model.add(Flatten())
model.add(Dense(units = 3, activation = "softmax"))
model.compile(loss='categorical_crossentropy', optimizer="adam", 
metrics=['accuracy'])


earlystop = EarlyStopping(monitor='val_loss', min_delta=0, patience=2, verbose=0, mode='min') 
model.fit (X_train, y_train,
       batch_size=64,
       callbacks = [earlystop],
       epochs=100,
       validation_data=(X_dev, y_dev),
       verbose=1)
scores = model.evaluate(X_test, y_testbatch_size=64)

print("Accuracy is: %.2f%%" %(scores[1] * 100))

Answer 1

我认为问题在于您应该将 encoded_docs 传递给您的 model.fit() 函数而不是 X_train，因为 encoded_docs 包含您的训练数据的标记，而 X_train 仍然只包含一个单词列表。此外，您必须确保 Embedding 层的 input_length 参数与您在 encoded_docs 中创建的这些标记化训练示例的长度相匹配。