ephemeral182 / udr-s2former_deraining Goto Github PK

Hi! It is a great and intersting work. But I am wondering the version of pytorch-lightning you used because I met some problem with the latest version (v2.x)

Can you provide pre-trained models on Rain200L and Rain200H？

@Ephemeral182
Is there a way to use the pretrained .pth files such as (udrs2former_agan.pth) in the training loop for further training. From what I have run, the training loop requires a checkpoint file with epoch, lr_optimizer, etc info which the .pth does not contain.

Is there any way to get the checkpoints file or hyperparameters of the final udrs2former_agan.pth file that your included in you github repo. Thanks.

Hello, thank you for your excellent work.
However, there are some issues with the provided code that have troubled me：
The saved model cannot be used when loaded in the test.

I would be grateful if you could provide me with the relevant assistance.

Cannot find UDR_S2Former.py file. would you please share it

Hello, how many GPUs are need for training and how long does it takes?

Hi, I enjoyed reading the paper and testing the project that you have developed.

I trained on my end and noticed that as the train loss and validation loss keeps decreasing (becomes negative even) the PSNR and SSIM still continue to increase.

When I train I got a train loss of -44.28 and validation loss of -29.18 but the PSNR is 27.73 and SSIM is .8729 (best case in my training). In my understanding shouldn't the loss be closer to 0 if you are trying to get a 1:1 correspondence between ground truth and the raindrop image.

This is a great job, but can the author provide code for visualizing uncertainty graphs so that the work can be better disseminated.