LOLv1 result

[whw2002]

Dear author, this is an excellent work. While using the provided weights to perform inference on the LOLv1 dataset, I encountered results as shown in the attached image. I’d like to ask what might be causing this issue, and whether you could kindly share the output images from your own inference as a reference?

[TaoWangzj]

Hi, thank you for your interest in our work! You can change the --grid_r, the performance of the model is affected by this parameter. I will share the results in the next few days.

[adpanda]

Dear author, this is an excellent work. While using the provided weights to perform inference on the LOLv1 dataset, I encountered results as shown in the attached image. I’d like to ask what might be causing this issue, and whether you could kindly share the output images from your own inference as a reference?

Excuse me, after you downloaded the dataset, did you make any modifications? I also ran a test following the same instructions as you, but I encountered an error in my output. I looked it up and found that it might be due to a mismatch between the model structure and the weights saved in the checkpoint. I'm not sure how to fix it. Below is my error message. Could you please tell me how you managed to run it successfully?

[whw2002]

亲爱的作者，这是一项非常出色的工作。在使用提供的权重对 LOLv1 数据集进行推理时，我遇到了如附图所示的结果。请问是什么原因导致了这个问题？您能否分享一下您自己推理的输出图像以供参考？

请问，您下载数据集后，有做过任何修改吗？我也按照您的说明运行了测试，但输出结果却出现了错误。我查了一下，发现可能是由于模型结构和检查点保存的权重不匹配造成的。我不知道该如何修复。以下是我的错误信息。请问您是如何成功运行的？

config/deg-unet-lol.yml

[adpanda]

亲爱的作者，这是一项非常出色的工作。在使用提供的权重对 LOLv1 数据集进行推理时，我遇到了如附图所示的结果。请问是什么原因导致了这个问题？您能否分享一下您自己推理的输出图像以供参考？

请问，您下载数据集后，有做过任何修改吗？我也按照您的说明运行了测试，但输出结果却出现了错误。我查了一下，发现可能是由于模型结构和检查点保存的权重不匹配造成的。我不知道该如何修复。以下是我的错误信息。请问您是如何成功运行的？

config/deg-unet-lol.yml

非常感谢您提供的这个信息，但是我按照这个修改了，还是出现一样的问题，你是只修改了这个地方吗？我用的是V100-32G的显卡，你也是吗？这是我的邮箱[email protected],希望可以和您交流一下