search

chilynn / sequence-labeling

307 stars 167 forks source link

why my loss decrease under 0 #25

Open tomsonsgs opened 7 years ago

tomsonsgs commented 7 years ago

loss is supposed to be close to and bigger than 0, self.loss = - (self.target_path_score - self.total_path_score),target_path_score should be smaller than total_path_score

tomsonsgs commented 7 years ago

i solve the problem by change the code if condition "i==0" by "j==0" in getTransition(y_train_batch) function,and loss come to 0 as expected,you all can check on that，and will this improve the final accuracy?someone can try that

tomsonsgs commented 7 years ago

@chilynn you can check on that and see if it is correct