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
when executing RNNPP encountered Nameerror : Python: NameError: free variable 'wt' referenced before assignment in enclosing scope on line 108 : 108. wt = tf.cond(tf.less(tf.reshape(tf.abs(w_t),[]),epilson),lambda:tf.sign(wt)*epilson, lambda:wt) #put in wrong position before
I think the variable names are messed up between w_t and wt but modifing it to 108. wt = tf.cond(tf.less(tf.reshape(tf.abs(w_t),[]),epilson),lambda:tf.sign(w_t)*epilson, lambda:w_t) #put in wrong position before
shows
InvalidArgumentError: Input to reshape is a tensor with 4064256 values, but the requested shape has 2016
....
The text was updated successfully, but these errors were encountered:
when executing RNNPP encountered Nameerror : Python: NameError: free variable 'wt' referenced before assignment in enclosing scope on line 108 :
108. wt = tf.cond(tf.less(tf.reshape(tf.abs(w_t),[]),epilson),lambda:tf.sign(wt)*epilson, lambda:wt) #put in wrong position before
I think the variable names are messed up between w_t and wt but modifing it to
108. wt = tf.cond(tf.less(tf.reshape(tf.abs(w_t),[]),epilson),lambda:tf.sign(w_t)*epilson, lambda:w_t) #put in wrong position before
shows
The text was updated successfully, but these errors were encountered: