dmn-tensorflow Variable not found when initializing

Variable not found when initializing

Open Chia-Hsuan-Lee opened this issue 8 years ago • 8 comments

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

Dec 30 '16 07:12 Chia-Hsuan-Lee

By the way i am running the dmn+ model .

Dec 30 '16 07:12 Chia-Hsuan-Lee

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?