Training problem

[id4su]

How to deal with this problem? Looking forward to your reply,thank you!

[xiaogang00]

I think you might modify the code and the key of "idx" is indicated in the dataloader script.

[id4su]

Thank you, after you help , i solved this before , but there is a new problem that is I can't close to your results(24.61).When I train and test in LOL dataset, the best final result is 22.90(use l_pix+l_vgg as you described in your paper) ,I'm really interested in your work , and I'd really appreciate it if you could help me.

[CaiShilv]

How to deal with this problem? Looking forward to your reply,thank you!

Excuse me, does the LOLv1 dataset you downloaded contain both the test and training sets in pairs (high and low)? The dataset I downloaded has 498 enhanced images in the training set and 500 low light images. However, in the test set, I found that there are 15 low-light images and only 2 enhanced images. This phenomenon is very strange. I am very much looking forward to your reply, thank you very much.

[luwenjie521542]

How to deal with this problem? Looking forward to your reply,thank you!

Hello, I have encountered the same problem that has been bothering me for a long time. Could you please tell me how you resolved it? I would greatly appreciate it！！！

[Shecyy]

How to deal with this problem? Looking forward to your reply,thank you!

Hello, how did you solve the bug shown in the picture?

[mawei-north]

如何处理这个问题？期待您的回复，谢谢！

您好，我遇到了困扰我很长时间的相同问题。你能告诉我你是怎么解决的吗？我将不胜感激 同学你好，我最近在复现这篇代码，也遇到了同样的这个问题，请问您当时是怎么解决这个问题的呢？

[lixiaofang-96]

我也遇到了这个问题，把和idx相关的代码注释掉了。主要是302行pbar.update('Test {}'.format(folder))，原来有idx，去掉也不影响。

[ChouMaoAn]

我也遇到了这个问题，把和idx相关的代码注释掉了。主要是302行pbar.update('Test {}'.format(folder))，原来有idx，去掉也不影响。

能具体的说明一下吗，谢谢

[ChouMaoAn]

Thank you, after you help , i solved this before , but there is a new problem that is I can't close to your results(24.61).When I train and test in LOL dataset, the best final result is 22.90(use l_pix+l_vgg as you described in your paper) ,I'm really interested in your work , and I'd really appreciate it if you could help me.

Hello, I have encountered this problem, too. Would you please tell me how this problem is solved? Thank you.

[ChouMaoAn]

I think you might modify the code and the key of "idx" is indicated in the dataloader script.

Hello, can you tell me how to solve this problem? This problem has been bothering me for a long time, thank you.

[ChouMaoAn]

我也遇到了这个问题，把和idx相关的代码注释掉了。主要是302行pbar.update('Test {}'.format(folder))，原来有idx，去掉也不影响。

你好，可以详细的说明一下吗，谢谢了

[lixiaofang-96]

就是idx_d是在输出测试图像的时候用到，表示第几张图像（302行pbar.update('Test {}'.format(folder))，原来有idx_d）。这部分代码针对视频写的，表示第几帧。单个测试图像不会用到idx_d，把idx_d = val_data['idx'].item()这一句代码注释掉，然后把302行改成pbar.update('Test {}'.format(folder))即可。

[ChouMaoAn]

就是idx_d是在输出测试图像的时候用到，表示第几张图像（302行pbar.update('Test {}'.format(folder))，原来有idx_d）。这部分代码针对视频写的，表示第几帧。单个测试图像不会用到idx_d，把idx_d = val_data['idx'].item()这一句代码注释掉，然后把302行改成pbar.update('Test {}'.format(folder))即可。

你好，是这样修改吗，但是我这样操作之后，还是出错了，是我操作失误了吗。不好意思，能不能看一下这个是什么问题，谢谢

[ChouMaoAn]

就是idx_d是在输出测试图像的时候用到，表示第几张图像（302行pbar.update('Test {}'.format(folder))，原来有idx_d）。这部分代码针对视频写的，表示第几帧。单个测试图像不会用到idx_d，把idx_d = val_data['idx'].item()这一句代码注释掉，然后把302行改成pbar.update('Test {}'.format(folder))即可。

你好，是这样修改吗，但是我这样操作之后，还是出错了，是我操作失误了吗。不好意思，能不能看一下这个是什么问题，谢谢

问题解决了，谢谢