这是我的训练模型，我基本上是按照这个教程https://www.youtube.com/watch?v=1lwddP0KUEg进行的操作，只是我必须使用stanza包来处理西班牙语版本：

import randomimport jsonimport pickleimport numpy as npimport pandas as pdimport nltkfrom nltk.tokenize.toktok import ToktokTokenizerimport stanzafrom tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import Dense, Activation, Dropoutfrom tensorflow.keras.optimizers import SGDtoktok = ToktokTokenizer()intents = json.loads(open("intents.json", "rb").read())words = []classes = []documents = []ignore_letters = ['¿','?', '!', '.', ',']nlp = stanza.Pipeline('es')for intent in intents['intents']:    for pattern in intent['patterns']:        word_list = toktok.tokenize(pattern)        words.extend(word_list)        documents.append((word_list, intent['tag']))        if intent['tag'] not in classes:            classes.append(intent['tag'])words = [nlp(word).to_dict() for word in words if word not in ignore_letters]  palabras = []for i in range(0,len(words)):        texto = words[i][0][0]["lemma"]    palabras.append(texto)    palabras = sorted(set(palabras))    classes = sorted(set(classes))pickle.dump(palabras, open('palabras.pkl', 'wb'))pickle.dump(classes, open('classes.pkl', 'wb'))training = []output_empty = [0] * len(classes)for document in documents:    bag = []    word_patterns = document[0]    word_patterns = [nlp(word.lower()).to_dict() for word in word_patterns]    for word in words:        bag.append(1) if word in word_patterns else bag.append(0)            output_row = list(output_empty)    output_row[classes.index(document[1])] = 1    training.append([bag, output_row])    random.shuffle(training)training = np.array(training, dtype="object")train_x = list(training[:, 0])train_y = list(training[:, 1])model = Sequential()model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))model.add(Dropout(0.5))model.add(Dense(64, activation='relu'))model.add(Dropout(0.5))model.add(Dense(len(train_y[0]), activation='softmax'))sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])hist = model.fit(np.array(train_x), np.array(train_y), epochs=200, batch_size=5, verbose=1)model.save('chatbotmodel.h5', hist)print('Listo')

问题在于当我尝试使用以下代码让模型预测类别时：

import randomimport jsonimport pickleimport numpy as npimport nltkfrom nltk.tokenize.toktok import ToktokTokenizerimport stanzafrom tensorflow.keras.models import load_modeltoktok = ToktokTokenizer()intents = json.loads(open('intents.json').read())words = pickle.load(open('palabras.pkl','rb'))classes = pickle.load(open('classes.pkl', 'rb'))model = load_model('chatbotmodel.h5')nlp = stanza.Pipeline('es')def clean_up_sentence(sentence):    sentence_words = toktok.tokenize(sentence)    words = [nlp(word).to_dict() for word in sentence_words]      palabras = []    for i in range(0,len(words)):            texto = words[i][0][0]["lemma"]        palabras.append(texto)        palabras = sorted(set(palabras))        return palabrasdef bag_of_words(sentence):    sentences_words = clean_up_sentence(sentence)    bag = [0] * len(words)    for w in sentences_words:        for i, word in enumerate(words):            if word == w:                bag[i] = 1        return np.array(bag)def predict_class(sentence):    bow = bag_of_words(sentence)    res = model.predict(np.array([bow]))[0]        return respredict_class('Hola, ¿cómo te va?)

出现了以下错误：

ValueError: Input 0 of layer sequential_1 is incompatible with the layer: expected axis -1 of input shape to have value 15 but received input with shape (None, 13)

有什么想法吗？因为我基本上是按照教程一步一步来的。用于训练的intents.json数据非常简单：

{"intents": [   {"tag": "respuestaSaludo",    "patterns": ["bien","¿quien es?","¿qué desea?"],    "responses": ["Mi nombre es Juan Carlos Bellido", "Soy Juan"]   },   {"tag": "respuestaPropuesta",    "patterns": ["no","no él gracias","no por ahora, aquí","de nuevo"],    "responses": ["ok, gracias","ok"]   }]}

编辑1：model.summary()：

Model: "sequential_1"_________________________________________________________________Layer (type)                 Output Shape              Param #   =================================================================dense_1 (Dense)              (None, 128)               2048      _________________________________________________________________dropout (Dropout)            (None, 128)               0         _________________________________________________________________dense_2 (Dense)              (None, 64)                8256      _________________________________________________________________dropout_1 (Dropout)          (None, 64)                0         _________________________________________________________________dense_3 (Dense)              (None, 2)                 130       =================================================================Total params: 10,434Trainable params: 10,434Non-trainable params: 0_________________________________________________________________

bow.shape：

def predict_class(sentence):    bow = bag_of_words(sentence)    return print(bow.shape)predict_class('quiero ver que sucede')

输出：

(13,)

回答：

据我所知 – 你的模型期望序列长度为15。你输入了13个标记。

尝试在你的序列末尾添加两个零：

bow = bag_of_words(sentence)bow = np.concatenate((bow, np.array([0, 0])), -1)res = model.predict(np.array([bow]))[0]