search

therne / dmn-tensorflow

Dynamic Memory Networks (https://arxiv.org/abs/1603.01417) in Tensorflow
240 stars 82 forks source link

Variable not found when initializing #7

Open Chia-Hsuan-Lee opened 7 years ago

Chia-Hsuan-Lee commented 7 years ago

First of all, i am excited to see this awesome implementation, your code is easy to read !

ValueError: Variable DMN/Episodic/Layer0/AttnGate/AttrGRU/Gates/Linear1/BatchNorm/DMN/Episodic/Layer0/AttnGate/AttrGRU_1/Gates/Linear1/BatchNorm/cond/DMN/Episodic/Layer0/AttnGate/AttrGRU_1/Gates/Linear1/BatchNorm/moments/normalize/mean/ExponentialMovingAverage/biased does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

I am on python3.5 I have searched the code and there isn't any variable declared with the error-prone "tf.variable()" All of them are declared with tf.getvariable() So i am not sure what is the problem here . Maybe you can help me ? Thanks really a lot ! @therne

Chia-Hsuan-Lee commented 7 years ago

By the way i am running the dmn+ model .

therne commented 7 years ago

I think it's because of the problem of batch normalization part, because this code was written when the TensorFlow version was 0.9. Can you remove the batch normalization code until the time I update?

therne commented 7 years ago

I'll fix the problem in days. Sorry! 😢

mmaaww commented 7 years ago

I went into the same problem. Any update on this?

therne commented 7 years ago

Sorry for late. I've been busy this past few months... I'll start working on this soon. 😢

mmaaww commented 7 years ago

that's fine, I got around this problem as temp solution for now.

thomasschijf commented 7 years ago

@mmaaww how?

BillPei commented 7 years ago

@mmaaww Any update on rhis and how to fix this problem?