创建一个 AI 聊天机器人，但出现回溯错误 [英] Creating an ai chatbot, but getting a traceback error
问题描述
我正在尝试在 python 中创建一个 AI 聊天框.我尝试按照本教程进行操作:
错误内容如下:
运行编号:VOB3W4日志目录:/tmp/tflearn_logs/---------------------------------训练样本:20验证样本:0————回溯(最近一次调用最后一次): 中的文件script.py"，第 91 行model.fit(训练，输出，n_epoch=1000，batch_size=8，show_metric=True)文件/usr/local/lib/python2.7/site-packages/tflearn/models/dnn.py"，第216行，合适回调=回调)文件/usr/local/lib/python2.7/site-packages/tflearn/helpers/trainer.py"，第339行，合适show_metric)文件/usr/local/lib/python2.7/site-packages/tflearn/helpers/trainer.py"，第 816 行，在 _traintflearn.is_training(True, session=self.session)文件/usr/local/lib/python2.7/site-packages/tflearn/config.py"，第 95 行，在 is_trainingtf.get_collection('is_training_ops')[0].eval(session=session)文件/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py"，第 731 行，在 eval 中返回 _eval_using_default_session(self, feed_dict, self.graph, session)_eval_using_default_session 中的文件/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py"，第 5579 行返回 session.run(张量，feed_dict)运行中的文件/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.py"，第 950 行run_metadata_ptr)文件/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.py"，第 1096 行，在 _runraise RuntimeError('试图使用一个关闭的会话.')运行时错误:尝试使用已关闭的会话. At start file "model.tflearn" 不存在，try/except 应该捕获错误当代码尝试加载此文件并运行 fit() 和 save()
尝试:model.load("model.tflearn")除了:model.fit(训练，输出，n_epoch=1000，batch_size=8，show_metric=True)模型.保存(模型.tflearn")但似乎此错误关闭了 tf.session()，因此它无法正确运行 fit().
如果你用 load() 删除 try/except 并且只保留 fit() 和 save()> 那么创建模型并保存在文件中就没有问题了.
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)模型.保存(模型.tflearn")创建文件 "model.ftlearn" 后，您可以再次使用 try/except 和 load()，如果不这样做它应该可以工作'不删除带有模型的文件.
更好的解决方案应该检查文件是否存在 - 但它将数据保存在几个文件中 "model.tflearn.index", "model.tflearn.meta" 和 >"model.tflearn.data-00000-of-00001" 所以它应该检查这个文件之一而不是 "model.tflearn"
使用
导入操作系统如果 os.path.exists("model.tflearn.meta"):model.load("model.tflearn")别的:model.fit(训练，输出，n_epoch=1000，batch_size=8，show_metric=True)模型.保存(模型.tflearn")代替
尝试:model.load("model.tflearn")除了:model.fit(训练，输出，n_epoch=1000，batch_size=8，show_metric=True)模型.保存(模型.tflearn")<小时>
看来这个问题至少存在 2 年:运行时错误:尝试在 tflearn 中使用关闭的会话
I'm trying to create an ai chatbox in python. I tried following this tutorial: https://techwithtim.net/tutorials/ai-chatbot/part-1/ but I'm getting a lot of errors of deprecations and getting some Traceback error. Here's the code:
import json
import random
import tensorflow
import tflearn
import numpy
import sys
import pickle
import nltk
from nltk.stem.lancaster import LancasterStemmer
stemmer = LancasterStemmer()
nltk.download('punkt')
with open("trainingData.json") as file:
data = json.load(file)
try:
with open("data.pickle", "rb") as f:
words, labels, training, output = pickle.load(f)
except:
words = []
labels = []
docs_x = []
docs_y = []
for intent in data["intents"]:
for pattern in intent["patterns"]:
wrds = nltk.word_tokenize(pattern)
words.extend(wrds)
docs_x.append(wrds)
docs_y.append(intent["tag"])
if intent["tag"] not in labels:
labels.append(intent["tag"])
words = [stemmer.stem(w.lower()) for w in words if w != "?"]
words = sorted(list(set(words)))
labels = sorted(labels)
training = []
output = []
out_empty = [0 for _ in range(len(labels))]
for x, doc in enumerate(docs_x):
bag = []
wrds = [stemmer.stem(w.lower()) for w in doc]
for w in words:
if w in wrds:
bag.append(1)
else:
bag.append(0)
output_row = out_empty[:]
output_row[labels.index(docs_y[x])] = 1
training.append(bag)
output.append(output_row)
training = numpy.array(training)
output = numpy.array(output)
with open("data.pickle", "wb") as f:
pickle.dump((words, labels, training, output), f)
tensorflow.reset_default_graph()
net = tflearn.input_data(shape=[None, len(training[0])])
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, len(output[0]), activation="softmax")
net = tflearn.regression(net)
model = tflearn.DNN(net)
try:
model.load("model.tflearn")
except:
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
model.save("model.tflearn")
def bag_of_words(s, words):
bag = [0 for _ in range(len(words))]
s_words = nltk.word_tokenize(s)
s_words = [stemmer.stem(word.lower()) for word in s_words]
for se in s_words:
for i, w in enumerate(words):
if w == se:
bag[i] = 1
return numpy.array(bag)
def chat():
print("Start talking with the bot (type quit to stop)!")
while True:
inp = input("You: ")
if inp.lower() == "quit":
break
results = model.predict([bag_of_words(inp, words)])
results_index = numpy.argmax(results)
tag = labels[results_index]
for tg in data["intents"]:
if tg['tag'] == tag:
responses = tg['responses']
print(random.choice(responses))
chat()
Here are the errors I'm getting. How can I fix the deprecation errors, the traceback error?
Here's the text of the error:
Run id: VOB3W4
Log directory: /tmp/tflearn_logs/
---------------------------------
Training samples: 20
Validation samples: 0
--
--
Traceback (most recent call last):
File "script.py", line 91, in <module>
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
File "/usr/local/lib/python2.7/site-packages/tflearn/models/dnn.py", line 216, in fit
callbacks=callbacks)
File "/usr/local/lib/python2.7/site-packages/tflearn/helpers/trainer.py", line 339, in fit
show_metric)
File "/usr/local/lib/python2.7/site-packages/tflearn/helpers/trainer.py", line 816, in _train
tflearn.is_training(True, session=self.session)
File "/usr/local/lib/python2.7/site-packages/tflearn/config.py", line 95, in is_training
tf.get_collection('is_training_ops')[0].eval(session=session)
File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 731, in eval
return _eval_using_default_session(self, feed_dict, self.graph, session)
File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 5579, in _eval_using_default_session
return session.run(tensors, feed_dict)
File "/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 950, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1096, in _run
raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
At start file "model.tflearn" doesn't exist and try/except should catch error when code try to load this file and run fit() and save()
try:
model.load("model.tflearn")
except:
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
model.save("model.tflearn")
but it seems this error closes tf.session() so it can't run fit()correctly.
If you remove try/except with load() and keep only fit() and save() then it has no problem to create model and save it in file.
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
model.save("model.tflearn")
After creating file "model.ftlearn" you can use again try/except with load() and it should work if you don't delete file with model.
Better solution should check if file exists - but it saves data in few files "model.tflearn.index", "model.tflearn.meta" and "model.tflearn.data-00000-of-00001" so it should check one of this file instead of "model.tflearn"
Use
import os
if os.path.exists("model.tflearn.meta"):
model.load("model.tflearn")
else:
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
model.save("model.tflearn")
instead of
try:
model.load("model.tflearn")
except:
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
model.save("model.tflearn")
EDIT: It seems this problem exists at least 2 years: RuntimeError: Attempted to use a closed Session in tflearn
这篇关于创建一个 AI 聊天机器人，但出现回溯错误的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
