Python &引用；ValueError配置格式不正确：'+；str（（配置）当使用tensorflow和keras时？
我正在使用图表方法进行聊天机器人响应。代码如下：Python &引用；ValueError配置格式不正确：'+；str（（配置）当使用tensorflow和keras时？,python,tensorflow,machine-learning,keras,deep-learning,Python,Tensorflow,Machine Learning,Keras,Deep Learning,我正在使用图表方法进行聊天机器人响应。代码如下： def classify(sentence): # generate probabilities from the model p = bow(sentence, words) d = len(p) f = len(documents) - 2 a = np.zeros([f, d]) tot = np.vstack((p, a)) with graph.as_default():
def classify(sentence):
# generate probabilities from the model
p = bow(sentence, words)
d = len(p)
f = len(documents) - 2
a = np.zeros([f, d])
tot = np.vstack((p, a))
with graph.as_default():
json_file = open('chatbot/intent.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
loaded_model.load_weights("chatbot/chatmodel.h5")
loaded_model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
results = loaded_model.predict(tot)[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
File "C:\python362\lib\site-packages\flask\app.py", line 1936, in dispatch_request
return self.view_functions[rule.endpoint](**req.view_args)
File "D:\INDUS-An-AI-E-Commerce-Web-Innovation-master\Ecommerce v1.0\app.py", line 1146, in get_bot_response
res = response(userText, '123', min_acceptable_price, user_offer, original_price)
File "D:\INDUS-An-AI-E-Commerce-Web-Innovation-master\Ecommerce v1.0\app.py", line 1076, in response
results = classify(sentence)
File "D:\INDUS-An-AI-E-Commerce-Web-Innovation-master\Ecommerce v1.0\app.py", line 977, in classify
loaded_model = model_from_json(loaded_model_json)
File "C:\python362\lib\site-packages\tensorflow\python\keras\saving\model_config.py", line 131, in model_from_json
return deserialize(config, custom_objects=custom_objects)
File "C:\python362\lib\site-packages\tensorflow\python\keras\layers\serialization.py", line 177, in deserialize
printable_module_name='layer')
File "C:\python362\lib\site-packages\tensorflow\python\keras\utils\generic_utils.py", line 347, in deserialize_keras_object
config, module_objects, custom_objects, printable_module_name)
File "C:\python362\lib\site-packages\tensorflow\python\keras\utils\generic_utils.py", line 291, in class_and_config_for_serialized_keras_object
raise ValueError('Improper config format: ' + str(config))
ValueError: Improper config format: {'intents': [{'tag': 'identity', 'patterns': ['Who is talking?', 'Who is this?', 'Who are you?', 'What is your name?', 'What can i call you?', .....