main.py

[Bruce-W12138]

您好作者，这个训练代码是否有问题，我按照您给出的方式设置了trainA和trainB但是仍然报错
‘Traceback (most recent call last):
File "D:\WorkProject\Image_Enhancement\night-enhancement-main\ENHANCENET.py", line 156, in train
real_A, _ = trainA_iter.next()
UnboundLocalError: local variable 'trainA_iter' referenced before assignment

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\WorkSoftware\Install\PyCharm Community Edition 2024.1.3\plugins\python-ce\helpers\pydev\pydevd.py", line 1546, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "D:\WorkSoftware\Install\PyCharm Community Edition 2024.1.3\plugins\python-ce\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "D:\WorkProject\Image_Enhancement\night-enhancement-main\main.py", line 75, in
main()
File "D:\WorkProject\Image_Enhancement\night-enhancement-main\main.py", line 71, in main
gan.train()
File "D:\WorkProject\Image_Enhancement\night-enhancement-main\ENHANCENET.py", line 159, in train
real_A, _ = trainA_iter.next()
AttributeError: '_SingleProcessDataLoaderIter' object has no attribute 'next'’

[Bruce-W12138]

我大概知道这个问题的原因了，还有最后一个问题想请教您，如果我要用新的light-effects数据集是否只需要获得J-init 即可作为trainB然后input作为trainA就可以进行训练了。那么testA和testB是用decomposition3获得的吗？还是说您的工作无法一步完成对光效应的抑制然后再做增强？

[jinyeying]

我大概知道这个问题的原因了，还有最后一个问题想请教您，如果我要用新的light-effects数据集是否只需要获得J-init 即可作为trainB然后input作为trainA就可以进行训练了。那么testA和testB是用decomposition3获得的吗？还是说您的工作无法一步完成对光效应的抑制然后再做增强？

trainB有normal light，trainA是low light，就可以完成对光效应的抑制和增强，主要看你数据怎么构造