You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Whenever I try to run the files in their default setting without modifications I get the following error shown in the headline.
This error is received in line 19 of the file "LstmUnit" (self.b = ...):
I get redirected to this file when calling the main.py function in the training setting, which calls the file "SeqUnit.py" which makes use of the "LstmUnit" file.
Does anybody have a reason for the conversion problems and may be able to help me with this issue?
The text was updated successfully, but these errors were encountered:
You have to change this line to: self.b = tf.compat.v1.get_variable('b', [4*self.hidden_size], initializer=tf.zeros_initializer(), dtype=tf.float32)
You will encounter several more errors like that, so I suggest you use my fork of wiki2bio which I have ported to TensorFlow 1.15 and I have corrected most bugs like this one.
Whenever I try to run the files in their default setting without modifications I get the following error shown in the headline.
This error is received in line 19 of the file "LstmUnit" (self.b = ...):
I get redirected to this file when calling the main.py function in the training setting, which calls the file "SeqUnit.py" which makes use of the "LstmUnit" file.
Does anybody have a reason for the conversion problems and may be able to help me with this issue?
The text was updated successfully, but these errors were encountered: