编辑1 ：按照akshat收到的答案，我使用了this教程来加载模型。 该代码已更新如下：
import tensorflow as tf
class Bot:
'''This class defines the routine of the bot'''
def __init__(self, presentation):
'''The bot presents itself'''
self.presentation = presentation
print('')
print(presentation)
def ask_question(self):
'''This method defines how the bot asks questions'''
print('')
self.answer = str(input('Please enter your question: ')).split(' ')
print('')
print('Thank you for your question. Let me check..')
def answer_question(self):
'''This method answer the user's questions'''
print('')
print(self.answer)
def load_model(self):
with tf.Session() as sess:
new_saver = tf.train.import_meta_graph('model.tflearn.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('./'))
print(sess.run('w1:0'))
bot = Bot('Good morning, my Name is BotPy')
question = bot.ask_question()
answer = bot.answer_question()
model = bot.load_model()
启动它会收到以下回溯：
2018-07-29 08:28:14.622798: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
WARNING:tensorflow:The saved meta_graph is possibly from an older release:
'model_variables' collection should be of type 'byte_list', but instead is of type 'node_list'.
Traceback (most recent call last):
File "/home/marco/PycharmProjects/chatBot/main.py", line 41, in <module>
model = bot.load_model()
File "/home/marco/PycharmProjects/chatBot/main.py", line 33, in load_model
new_saver = tf.train.import_meta_graph('model.tflearn.meta')
File "/home/marco/PycharmProjects/chatBot/venv/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 1960, in import_meta_graph
**kwargs)
File "/home/marco/PycharmProjects/chatBot/venv/lib/python3.5/site-packages/tensorflow/python/framework/meta_graph.py", line 790, in import_scoped_meta_graph
ops.prepend_name_scope(value, scope_to_prepend_to_names))
File "/home/marco/PycharmProjects/chatBot/venv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3613, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/home/marco/PycharmProjects/chatBot/venv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3673, in _as_graph_element_locked
"graph." % repr(name))
KeyError: "The name 'Adam' refers to an Operation not in the graph."
原始问题：我正在尝试构建一个聊天机器人。
在this教程之后，我已经有了一个jupyter笔记本解决方案，该解决方案可以与已经训练好的模型一起使用。
import nltk
from nltk.stem.lancaster import LancasterStemmer
import numpy as np
import tflearn
import tensorflow as tf
import random
import json
from ._conv import register_converters as _register_converters
stemmer = LancasterStemmer()
with open('intents.json') as json_data:
intents = json.load(json_data)
words = []
classes = []
documents = []
ignore_words = ['?']
# loop through each sentence in our intents patterns
for intent in intents['intents']:
for pattern in intent['patterns']:
# tokenize each word in the sentence
w = nltk.word_tokenize(pattern)
# add to our words list
words.extend(w)
# add to documents in our corpus
documents.append((w, intent['tag']))
# add to our classes list
if intent['tag'] not in classes:
classes.append(intent['tag'])
# stem and lower each word and remove duplicates
words = [stemmer.stem(w.lower()) for w in words if w not in ignore_words]
words = sorted(list(set(words)))
# remove duplicates
classes = sorted(list(set(classes)))
print (len(documents), "documents")
print (len(classes), "classes", classes)
print (len(words), "unique stemmed words", words)
20 documents
6 classes ['goodbye', 'greeting', 'hours', 'opentoday', 'payments', 'thanks']
32 unique stemmed words ["'s", 'acceiv', 'anyon', 'ar', 'bye', 'card', 'cash', 'credit', 'day', 'do', 'good', 'goodby', 'hello', 'help', 'hi', 'hour', 'how', 'is', 'lat', 'mastercard', 'on', 'op', 'see', 'tak', 'thank', 'that', 'ther', 'today', 'what', 'when', 'yo', 'you']
# create our training data
training = []
output = []
# create an empty array for our output
output_empty = [0] * len(classes)
# training set, bag of words for each sentence
for doc in documents:
# initialize our bag of words
bag = []
# list of tokenized words for the pattern
pattern_words = doc[0]
# stem each word
pattern_words = [stemmer.stem(word.lower()) for word in pattern_words]
# create our bag of words array
for w in words:
bag.append(1) if w in pattern_words else bag.append(0)
# output is a '0' for each tag and '1' for current tag
output_row = list(output_empty)
output_row[classes.index(doc[1])] = 1
training.append([bag, output_row])
# shuffle our features and turn into np.array
random.shuffle(training)
training = np.array(training)
# create train and test lists
train_x = list(training[:,0])
train_y = list(training[:,1])
# reset underlying graph data
tf.reset_default_graph()
# Build neural network
net = tflearn.input_data(shape=[None, len(train_x[0])])
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, len(train_y[0]), activation='softmax')
net = tflearn.regression(net)
# Define model and setup tensorboard
model = tflearn.DNN(net, tensorboard_dir='tflearn_logs')
# Start training (apply gradient descent algorithm)
model.fit(train_x, train_y, n_epoch=1000, batch_size=8, show_metric=True)
model.save('model.tflearn')
Training Step: 2999 | total loss: 0.01771 | time: 0.006s
| Adam | epoch: 1000 | loss: 0.01771 - acc: 0.9999 -- iter: 16/20
Training Step: 3000 | total loss: 0.01754 | time: 0.009s
| Adam | epoch: 1000 | loss: 0.01754 - acc: 1.0000 -- iter: 20/20
--
INFO:tensorflow:/home/marco/PycharmProjects/chatBot/model.tflearn is not in all_model_checkpoint_paths. Manually adding it.
# save all of our data structures
import pickle
pickle.dump( {'words':words, 'classes':classes, 'train_x':train_x, 'train_y':train_y}, open( "training_data", "wb" ) )
data = pickle.load( open( "training_data", "rb" ) )
words = data['words']
classes = data['classes']
train_x = data['train_x']
train_y = data['train_y']
# import our chat-bot intents file
import json
with open('intents.json') as json_data:
intents = json.load(json_data)
# load our saved model
model.load('./model.tflearn')
INFO:tensorflow:Restoring parameters from /home/marco/PycharmProjects/chatBot/model.tflearn
def clean_up_sentence(sentence):
# tokenize the pattern
sentence_words = nltk.word_tokenize(sentence)
# stem each word
sentence_words = [stemmer.stem(word.lower()) for word in sentence_words]
return sentence_words
# return bag of words array: 0 or 1 for each word in the bag that exists in the sentence
def bow(sentence, words, show_details=False):
# tokenize the pattern
sentence_words = clean_up_sentence(sentence)
# bag of words
bag = [0]*len(words)
for s in sentence_words:
for i,w in enumerate(words):
if w == s:
bag[i] = 1
if show_details:
print ("found in bag: %s" % w)
return(np.array(bag))
# create a data structure to hold user context
context = {}
ERROR_THRESHOLD = 0.25
def classify(sentence):
# generate probabilities from the model
results = model.predict([bow(sentence, words)])[0]
# filter out predictions below a threshold
results = [[i,r] for i,r in enumerate(results) if r>ERROR_THRESHOLD]
# sort by strength of probability
results.sort(key=lambda x: x[1], reverse=True)
return_list = []
for r in results:
return_list.append((classes[r[0]], r[1]))
# return tuple of intent and probability
return return_list
def response(sentence, userID='123', show_details=False):
results = classify(sentence)
# if we have a classification then find the matching intent tag
if results:
# loop as long as there are matches to process
while results:
for i in intents['intents']:
# find a tag matching the first result
if i['tag'] == results[0][0]:
# set context for this intent if necessary
if 'context_set' in i:
if show_details: print ('context:', i['context_set'])
context[userID] = i['context_set']
# check if this intent is contextual and applies to this user's conversation
if not 'context_filter' in i or \
(userID in context and 'context_filter' in i and i['context_filter'] == context[userID]):
if show_details: print ('tag:', i['tag'])
# a random response from the intent
return print(random.choice(i['responses']))
results.pop(0)
输出示例：
response('Hello')
>>Hi there, how can I help?
response('open')
>>Our hours are 9am-8pm every day
我的目标是使用面向对象的程序（下面我想到的基本结构）来构造聊天机器人本身：
class Bot:
'''This class defines the routine of the bot'''
def __init__(self, presentation):
'''The bot presents itself'''
self.presentation = presentation
print('')
print(presentation)
def ask_question(self):
'''This method defines how the bot asks questions'''
print('')
self.answer = str(input('Please enter your question: ')).split(' ')
print('')
print('Thank you for your question. Let me check..')
def answer_question(self):
'''This method answer the user's questions'''
print('')
print(self.answer)
bot = Bot('Good morning, my Name is BotPy')
question = bot.ask_question()
answer = bot.answer_question()
我的问题：
我每次启动聊天机器人时都必须训练模型，还是可以从目录中调用已经训练过的模型？
如果上述两种解决方案之一是正确的，我该如何实施正确的解决方案？