训练时出错，使用最新版配置文件2020Track2.yml进行训练出现错误

[LiYAnErr]

（1）问题一：KeyError: 'netDeg' Traceback (most recent call last): File "train.py", line 481, in main() File "train.py", line 171, in main main_worker(0, 1, opt, args) File "train.py", line 305, in main_worker model.optimize_parameters(current_step) File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/deg_sr_model.py", line 235, in optimize_parameters loss_dict = self.optimize_trans_models(step, loss_dict) File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/deg_sr_model.py", line 149, in optimize_trans_models self.set_optimizer(names=["netDeg"], operation="zero_grad") File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/base_model.py", line 174, in set_optimizer getattr(self.optimizers[name], operation)() KeyError: 'netDeg'

（2）问题二：KeyError：'lr_adv' Traceback (most recent call last): File "train.py", line 481, in main() File "train.py", line 171, in main main_worker(0, 1, opt, args) File "train.py", line 305, in main_worker model.optimize_parameters(current_step) File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/deg_sr_model.py", line 235, in optimize_parameters loss_dict = self.optimize_trans_models(step, loss_dict) File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/deg_sr_model.py", line 164, in optimize_trans_models self.netD1, self.losses["lr_adv"], KeyError: 'lr_adv'

这两个问题都是训练时需要用到的键值在配置文件中没有。

• 问题一：KeyError: 'netDeg' 是在2020Track2.yml缺少优化器netDeg
• 问题二：KeyError：'lr_adv' 是在2020Track2.yml中缺少损失函数lr_adv

请问作者是2020Track2.yml确有上述问题，还是我某些文件没有用到最新版呢？谢谢作者～

[mrgreen3325]

（1）问题一：KeyError: 'netDeg' Traceback (most recent call last): File "train.py", line 481, in main() File "train.py", line 171, in main main_worker(0, 1, opt, args) File "train.py", line 305, in main_worker model.optimize_parameters(current_step) File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/deg_sr_model.py", line 235, in optimize_parameters loss_dict = self.optimize_trans_models(step, loss_dict) File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/deg_sr_model.py", line 149, in optimize_trans_models self.set_optimizer(names=["netDeg"], operation="zero_grad") File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/base_model.py", line 174, in set_optimizer getattr(self.optimizers[name], operation)() KeyError: 'netDeg'

（2）问题二：KeyError：'lr_adv' Traceback (most recent call last): File "train.py", line 481, in main() File "train.py", line 171, in main main_worker(0, 1, opt, args) File "train.py", line 305, in main_worker model.optimize_parameters(current_step) File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/deg_sr_model.py", line 235, in optimize_parameters loss_dict = self.optimize_trans_models(step, loss_dict) File "/6T/home/dell/LiYAnErr/UseMyDataRunBaseline/UnpairedSR-master/codes/config/PDM-SR/models/deg_sr_model.py", line 164, in optimize_trans_models self.netD1, self.losses["lr_adv"], KeyError: 'lr_adv'

这两个问题都是训练时需要用到的键值在配置文件中没有。

• 问题一：KeyError: 'netDeg' 是在2020Track2.yml缺少优化器netDeg
• 问题二：KeyError：'lr_adv' 是在2020Track2.yml中缺少损失函数lr_adv

请问作者是2020Track2.yml确有上述问题，还是我某些文件没有用到最新版呢？谢谢作者～

Hello, did you solve this problem? I am going to try to use the 2020Track2.yml, Is there any I need to pay attention?

[LaurenceQ]

您好，我遇见了同样的问题，请问您是如何解决这个问题的？