ValueError:传递的save_path不是有效的检查点:C:\Users\User\model.tflea

Question

我一直在尝试创建一个聊天机器人，但一直收到以下错误。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:UsersUserAnaconda3envsnewbotlibsite-packagestflearnmodelsdnn.py", line 308, in load
self.trainer.restore(model_file, weights_only, **optargs)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestflearnhelperstrainer.py", line 490, in restore
self.restorer.restore(self.session, model_file)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestensorflowpythontrainingsaver.py", line 1278, in restore
compat.as_text(save_path))
ValueError: The passed save_path is not a valid checkpoint: C:UsersUsermodel.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:UsersUserAnaconda3envsnewbotlibsite-packagestflearnmodelsdnn.py", line 216, in fit
callbacks=callbacks)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestflearnhelperstrainer.py", line 339, in fit
show_metric)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestflearnhelperstrainer.py", line 816, in _train
tflearn.is_training(True, session=self.session)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestflearnconfig.py", line 95, in is_training
tf.get_collection('is_training_ops')[0].eval(session=session)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestensorflowpythonframeworkops.py", line 731, in eval
return _eval_using_default_session(self, feed_dict, self.graph, session)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestensorflowpythonframeworkops.py", line 5579, in _eval_using_default_session
return session.run(tensors, feed_dict)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestensorflowpythonclientsession.py", line 950, in run
run_metadata_ptr)
File "C:UsersUserAnaconda3envsnewbotlibsite-packagestensorflowpythonclientsession.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
• TensorFlow 1.14.0
• TFLearn 0.3.2

提前谢谢！

Answer 1

将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")

我认为问题的出现是因为你正在创建和重置一个模型，然后请求加载它，然后框架就丢失了。

Answer 2

首先，从这个错误消息

ValueError: The passed save_path is not a valid checkpoint: C:UsersUsermodel.tflearn

看起来CCD_ 1不存在。

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