chengxihan / hanet-cd Goto Github PK

Traceback (most recent call last):
File "Output_Results.py", line 39, in
model = torch.load(path)
File "/root/miniconda3/lib/python3.8/site-packages/torch/serialization.py", line 712, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/root/miniconda3/lib/python3.8/site-packages/torch/serialization.py", line 1046, in _load
result = unpickler.load()
File "/root/miniconda3/lib/python3.8/site-packages/torch/serialization.py", line 1039, in find_class
return super().find_class(mod_name, name)
ModuleNotFoundError: No module named 'models.MSPSNetHCX'
我在加载您的训练结果模型时出现了以下情况，似乎在您的训练结果之后还修改过代码结构，不知道您是否方便更新代码，或者给我字典形式的模型参数

Traceback (most recent call last):
File "E:\Futherstudy\change-detection\reproduction\HANet-CD-main\test.py", line 36, in
model = torch.load(path)
File "D:\ANACONDA\envs\d2l\lib\site-packages\torch\serialization.py", line 712, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "D:\ANACONDA\envs\d2l\lib\site-packages\torch\serialization.py", line 1049, in _load
result = unpickler.load()
File "D:\ANACONDA\envs\d2l\lib\site-packages\torch\serialization.py", line 1042, in find_class
return super().find_class(mod_name, name)
ModuleNotFoundError: No module named 'models.MSPSNetHCX'

Process finished with exit code 1

I want to check the results, and request you to please share the pre-trained modea l. i do not have good GPU to train.

Author I would like to ask a question, why is the log recorded in the val section of the train code using mean_train_metrics?