我的代码中有一个问题，其中训练聊天机器人的函数有一些错误。
这个想法是让tensorflow v2从Sqlite3数据库训练。但是每当我修正一个错误时，另一个错误就会出现。
下面我留下我正在使用的代码和规范。
'list'对象没有属性'dtype'/inputs = tf.keras.layers。嵌入(1000,64,input_length=10)(input)▶ Python 3.10.9
▶ openai == 0.25.0
▶ tensorflow == 3.9.0
▶ pyttsx3 == 2.90
▶ speech_recognition == 3.9.0
▶ requests == 2.28.1
▶ numpy == 1.24.0
▶ nltk == 3.8
import sqlite3
import numpy as np
import openai
import requests
import speech_recognition as sr
import pyttsx3
import tensorflow as tf
DATABASE = "chatbot.db"
# Connection to the database and creation of the "conversas" table with two columns "pergunta" / "resposta"
conn = sqlite3.connect(DATABASE)
cursor = conn.cursor()
cursor.execute("CREATE TABLE IF NOT EXISTS conversations (question text, answer text)")
conn.commit()
# Voice recognition function
def recognize_voice():
# Create a voice recognition object
r = sr.Recognizer()
# Start capturing audio from the microphone
with sr.Microphone() as source:
print("n▶ ")
audio = r.listen(source)
# Use the OS's voice recognition to convert the audio to text
try:
text = r.recognize_google(audio, language='pt-BR')
except sr.UnknownValueError:
print("I didn't understand what you said")
text = None
if text.strip() == "":
print("No text could be recognized")
text = None
return text
## Voice synthesis function
def synthesize_voice(text):
# Initialize the voice synthesis engine
engine = pyttsx3.init()
# Set the voice synthesis language
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[-2].id)
# Voice synthesis
engine.say(text)
# Run the voice synthesis
engine.runAndWait()
# Function to search Wikipedia
def search_wikipedia(keyword):
# Search Wikipedia for the specified topic
url = f"https://pt.wikipedia.org/w/api.php?action=opensearch&format=json&search={keyword}"
response = requests.get(url)
data = response.json()
# Check if there were any results for the search
if len(data[1]) > 0:
# Get the URL of the results page
page_url = data[3][0]
# Make a new HTTP call to get the content of the results page
page_response = requests.get(page_url)
page_html = page_response.text
# Extract the first paragraph from the page
start = page_html.index("<p>")
end = page_html.index("</p>")
paragraph = page_html[start:end+4]
return paragraph
else:
return "No information could be found about the specified topic."
# Function to train the neural network
def train_conversation_model(vocabulary_size=10000, maximum_sequence_length=100, embedding_dimension=32):
# Open a connection to the database
conn = sqlite3.connect(DATABASE)
# Create a cursor to access the data
cursor = conn.cursor()
# Execute a query to retrieve the data from the database
cursor.execute("SELECT question, answer FROM conversations")
data = cursor.fetchall()
# Define the inputs and outputs of the model
inputs = []
outputs = []
# Iterate over the data and separate the inputs (strings) from the outputs (labels)
for datum in data:
inputs.append(datum[0])
outputs.append(datum[1])
# Transform the inputs into tensors with TensorFlow
if inputs is not None and inputs != []:
print("Attention: the 'inputs' variable is invalid!")
else:
inputs = [str(i) for i in inputs]
inputs = tf.keras.preprocessing.text.Tokenizer(num_words=vocabulary_size, lower=True).texts_to_sequences(inputs)
inputs = tf.keras.preprocessing.sequence.pad_sequences(inputs, maxlen=maximum_sequence_length)
# Add an embedding layer
inputs = tf.keras.layers.Embedding(1000, 64, input_length=10)(inputs)
# Define the model
model = tf.keras.Sequential()
model.add(tf.keras.layers.LSTM(units=64, return_sequences=True))
model.add(tf.keras.layers.LSTM(units=32))
model.add(tf.keras.layers.Dense(units=1, activation='sigmoid'))
# Compile the model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# Train the model
model.fit(inputs, outputs, epochs=10, batch_size=64)
# Save the trained model
model.save_weights('minha_rede_neural.h5')
# Use the openAI GPT-3 library to generate the chatbot's responses.
def generate_response(question):
openai.api_key = "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"
model_engine = "text-davinci-003"
prompt = (f"What is the answer to the following question?n{question}")
completions = openai.Completion.create(
engine=model_engine,
prompt=prompt,
max_tokens=2048,
n=1,
stop=None,
temperature=0.8,
top_p=1,
frequency_penalty=1,
presence_penalty=1,
)
message = completions.choices[0].text
return message.strip()
## Main function to interact with the chatbot
def chatbot():
while True:
print("nChoose the interaction method:")
print("1. Voice")
print("2. Chat")
print("3. Train the neural network")
print("4. Exit")
option = input("Enter the desired option: ")
if option == "1":
# Voice interaction
question = recognize_voice()
if question is None:
continue
response = generate_response(question)
synthesize_voice(response)
elif option == "2":
# Chat interaction
question = input("nYou: ")
response = generate_response(question)
print(f"nChatbot: {response}")
elif option == "3":
# Train the neural network
train_conversation_model('chatbot.db')
elif option == "4":
# Exit the chatbot
break
# Start the chatbot
chatbot()
我认为问题是将输入定义为填充序列，然后用inputs = tf.keras.layers.Embedding(1000, 64, input_length=10)(inputs)覆盖它。嵌入层需要成为你的神经网络架构的一部分，所以试着删除这一行，并调整你的模型定义成这样的东西(没有测试过):
model.add(tf.keras.layers.Embedding(1000, 64, input_length=10))
model.add(tf.keras.layers.LSTM(units=64, return_sequences=True))
model.add(tf.keras.layers.LSTM(units=32))
model.add(tf.keras.layers.Dense(units=1, activation='sigmoid'))