search

Alik033 / Lit-Net

6 stars 1 forks source link

where can i found checkpoints #1

Closed 289282737 closed 6 days ago

289282737 commented 6 days ago

HELLO！Alik033! I have star. I train the moudle,but the SSIM so low,and MSE so high. This is my question -------loading model for generator None No checkpoints found for netG and netD! retraining

Please answer me,Thank you! I can understand English and Chinese! C:\ProgramData\anaconda3\envs\test\python.exe D:\Lit-Net-main\Enhancment\train.py C:\ProgramData\anaconda3\envs\test\lib\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( C:\ProgramData\anaconda3\envs\test\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=VGG16_Weights.IMAGENET1K_V1. You can also use weights=VGG16_Weights.DEFAULT to get the most up-to-date weights. warnings.warn(msg) loading model for generator None No checkpoints found for netG and netD! retraining Epoch : 1 | (17/2287) | mse: 0.8905353546142578 | vgg: 0.159453883767128 | ssim: 0.13122130930423737

Alik033 commented 6 days ago

Thanks for showing interest in Lit-Net. I have uploaded the checkpoints for the UIEB and LSUI datasets. I will upload the checkpoints for the remaining datasets shortly.

Regarding the SSIM and MSE, during training, you see the SSIM and MSE loss value. It is not the SSIM and MSE on the test set. First, you train for a few epochs, test it with a test set, and check the SSIM and MSE.

289282737 commented 6 days ago

I have understood. Thank you very much for your reply and assistance!
 

罗凯伦 @.***

 

------------------ 原始邮件 ------------------ 发件人: "Alik @.>; 发送时间: 2024年11月19日(星期二) 下午3:34 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [Alik033/Lit-Net] where can i found checkpoints (Issue #1)

Thanks for showing interest in Lit-Net. I have uploaded the checkpoints for the UIEB and LSUI datasets. I will upload the checkpoints for the remaining datasets shortly.

Regarding the SSIM and MSE, during training, you see the SSIM and MSE loss value. It is not the SSIM and MSE on the test set. First, you train for a few epochs, test it with a test set, and check the SSIM and MSE.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>