test_data in get_batch_by_q ?
ma-biao opened this issue · comments
In get_batch_by_q of dataset.py :
if validation:
fact_ls = self.valid_fact_ls
else:
fact_ls = self.test_fact_ls
So the fact_ls is either valid_data or test_data, and in E-step of train loop, test_data is used for train.
Is that test data leakage? Looking forward to your reply.