-
Notifications
You must be signed in to change notification settings - Fork 6
Open
Description
In Training phase i get this error:
UnboundLocalError Traceback (most recent call last)
<ipython-input-30-730ad33b5889> in <module>()
110 model.train(False) # evaluation을 위해, 훈련 X
111 #global best_idx
--> 112 best_train_F, new_train_F, _,_ = evaluating(model, test_train_data, best_train_F, epoch)
113 best_test_F, new_test_F, _,opts.best_idx = evaluating(model, test_data, best_test_F, epoch)
114 # validation의 결과가 best면 save를 True로, 모델이 저장되도록
<ipython-input-29-76c9c4a8fd6b> in evaluating(model, datas, best_F, epoch, display_confusion_matrix)
118 # new_F : 현재 sample의 F score
119 # save : 최고 F score를 갱신하면 save = True를 return
--> 120 return best_F, new_F, save, best_idx
121 print(best_idx)
UnboundLocalError: local variable 'best_idx' referenced before assignment
Any idea how to solve it?
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels