Debatrix / UPCL

Rethinking Class Incremental Learning from a Dynamic Imbalanced Learning Perspective
0 stars 0 forks source link

It won't run with the default settings #1

Closed caoshuai888 closed 5 months ago

caoshuai888 commented 5 months ago

感谢您对 CIL 领域的贡献! 当我下载upcl代码后,用默认设置运行代码,出现了下面的问题,您能帮忙看看吗? 2024-06-12 21:13:55,771 [trainer.py] => 'UPCL_iCaRL' object has no attribute 'k' Traceback (most recent call last): File "/home/ps/dl/shuai/UPCL-main/trainer.py", line 82, in _train model.incremental_train(data_manager) File "/home/ps/dl/shuai/UPCL-main/models/icarl.py", line 74, in incremental_train self._train(self.train_loader, self.test_loader) File "/home/ps/dl/shuai/UPCL-main/models/upcl.py", line 273, in _train k = min(fea_mask.sum(0).min(), self.k) AttributeError: 'UPCL_iCaRL' object has no attribute 'k'

Debatrix commented 5 months ago

Thanks for the reminder, this issue was fixed in the last Commit. The k in line 273 is a hyperparameter in KCL Loss, I tried to use it to improve performance, but found that it didn't matter, so I removed the relevant code, and here is the part that was left behind.