-
Notifications
You must be signed in to change notification settings - Fork 33
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
NAFNet版本LED疑问 #24
Comments
您好!我们基于NAFNet部分实验的配置文件也已经开源在了我们的repo当中:Pretrain、Fine-tune。 对于不同的相机(CMOS传感器),LED可能需要调整fine-tune的策略,建议您在拍摄时候可以多拍摄一份测试场景(2-3即可)(采集策略可以参考我们最新arxiv论文的Sec 4)。调整fine-tune策略并在测试场景上测试有效后,在最终部署时可以使用全部场景(训练+测试)进行训练,最终的模型作为部署模型。 如果您能提供更多的有关输入输出、fine-tune策略、使用的预训练模型的信息,也许我们能提供更多帮助。 btw, 如果LED对您的项目有帮助的话,希望您可以帮我们点个star🌟,这将是对我们进一步科研的莫大鼓励!感谢! |
我们的benchmark脚本目前仅支持unet的结构,强行载入NAFNet结构的话会导致参数不匹配。 但是我们设置了 |
能看下您的 |
您可以在finetune阶段中将图像保存下来看看吗?看看是否有这种问题。 |
finetune阶段保存下来的图片是正常的 |
I also encountered the problem of fine-tuning on other datasets and found that the effects of NEFNet and Restormer are not as good as the effects of Unet. Could you please let me know if you have solved the problem? I would be grateful if you could reply to me. |
您好,我在您提供的的NAFnet预训练网络权重下,进行微调。但是部署的时候图片出现明显的红色噪点,请问您在进行NAFNet部分实验是如何操作的,还是我需要调整finetune部分的细节
The text was updated successfully, but these errors were encountered: