用tensorflow进行训练时遇到以下问题:
WARNING:tensorflow:Issue encountered when serializing update_ops.
Type is unsupported, or the types of the items don't match field type in CollectionDef. Note this is a warning and probably safe to ignore.
'list' object has no attribute 'name'
回答:https://github.com/tflearn/tflearn/issues/190
“ This warning shouldn't impact your training, this is just linked with variable serialization when saving the model, I will check what is wrong there.
In general, LSTM performs better than simpleRNN as they can 'remember' information longer, that can explain the difference in accuracy you noticed.”
翻译:
“这个警告不影响训练,仅仅与变量存储时的变量序列化有关。我将会检查哪里出错了。
一般,LSTM比简单的RNN效果要好,因为它们可以记忆更久的信息,这可以解释你注意到的准确率的差异”