ValueError: The passed save_path is not a valid checkpoint: C:\Users\User\model.tflearn

Question

我一直在尝试创建一个聊天机器人，但我一直收到以下错误。我是 TensorFlow 的初学者。

Traceback (most recent call last):
  File "main.py", line 78, in <module>
    model.load("model.tflearn")
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tflearn\models\dnn.py", line 308, in load
    self.trainer.restore(model_file, weights_only, **optargs)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tflearn\helpers\trainer.py", line 490, in restore
    self.restorer.restore(self.session, model_file)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tensorflow\python\training\saver.py", line 1278, in restore
    compat.as_text(save_path))
ValueError: The passed save_path is not a valid checkpoint: C:\Users\User\model.tflearn

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "main.py", line 80, in <module>
    model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tflearn\models\dnn.py", line 216, in fit
    callbacks=callbacks)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tflearn\helpers\trainer.py", line 339, in fit
    show_metric)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tflearn\helpers\trainer.py", line 816, in _train
    tflearn.is_training(True, session=self.session)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tflearn\config.py", line 95, in is_training
    tf.get_collection('is_training_ops')[0].eval(session=session)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tensorflow\python\framework\ops.py", line 731, in eval
    return _eval_using_default_session(self, feed_dict, self.graph, session)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tensorflow\python\framework\ops.py", line 5579, in _eval_using_default_session
    return session.run(tensors, feed_dict)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\site-packages\tensorflow\python\client\session.py", line 950, in run
    run_metadata_ptr)
  File "C:\Users\User\Anaconda3\envs\newbot\lib\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.

这是我的 TensorFlow 代码：

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")

我正在使用：

Python 3.6.9
张量流 1.14.0
TFLearn 0.3.2

提前致谢！

Answer 1

首先，从这个错误信息

ValueError: The passed save_path is not a valid checkpoint: C:\Users\User\model.tflearn

看起来 C:\Users\User\model.tflearn 不存在。

其次，你在异常处理块中有model.fit函数。是故意的吗？我想您只有在能够成功加载模型的情况下才想继续执行拟合和保存功能。

Answer 2

将您的 Tensorflow 代码更改为：

try:
    model.load('model.tflearn')
except:
    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)

    model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
    model.save("model.tflearn")

我认为问题的发生是因为您正在创建和重置模型，然后请求加载它，然后框架丢失了。

ValueError: The passed save_path is not a valid checkpoint: C:\Users\User\model.tflearn

ValueError: The passed save_path is not a valid checkpoint: C:\Users\User\model.tflearn

python-3.x

tensorflow

machine-learning

chatbot

tflearn