3

我正在关注一本关于构建聊天机器人的书，并在尝试开始交互式学习时继续遇到此错误。

完整的错误是这样的：

回溯（最后一次调用）：文件“train_initialize.py”，第 18 行，在 agent = Agent("horoscope_domain.yml", policies = [MemoizationPolicy(), KerasPolicy()]) 文件“C:\Users\Max\ AppData\Local\Programs\Python\Python37\lib\site-packages\rasa_core\policies\keras_policy.py”，第 31 行，如果 KerasPolicy.is_using_tensorflow() 而不是图形，则在init 中：文件“C:\Users\Max\AppData \Local\Programs\Python\Python37\lib\site-packages\rasa_core\policies\keras_policy.py"，第 48 行，在 is_using_tensorflow return keras.backend._BACKEND == "tensorflow" AttributeError: module 'keras.backend' has no属性“_BACKEND”

我的代码看起来像这样'''

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

from rasa_core import utils
import tensorflow.keras.backend
from rasa_core.agent import Agent
from rasa_core.policies.keras_policy import KerasPolicy
from rasa_core.policies.memoization import MemoizationPolicy
from rasa_core.policies.sklearn_policy import SklearnPolicy

if __name__ == '__main__':
    utils.configure_colored_logging(loglevel="DEBUG")

    training_data_file = './data/stories.md'
    model_path = './models/dialogue'
    agent = Agent("horoscope_domain.yml", policies = [MemoizationPolicy(), KerasPolicy()])

    training_data = agent.load_data(training_data_file)

    agent.train(training_data, augmentation_factor = 50, epochs = 500, batch_size = 10, validation_split = 0.2)
    agent.persist(model_path)

'''

4

1 回答 1

0

看起来像过时的 API 代码；打开错误跟踪中的文件，并替换._BACKENDw/ .backend()：

# In "C:\Users\Max\AppData\Local\Programs\Python\Python37\lib\site-packages
# \rasa_core\policies\keras_policy.py", line 48:

# return keras.backend._BACKEND == "tensorflow" # <-- DELETE
return keras.backend.backend() == "tensorflow"  # <-- PASTE
于 2019-11-12T23:06:12.653 回答