zhuyr97 / wgws-net Goto Github PK

Hello! This is a very good work. I am very interested in your work. I wonder if you can provide the sampled dataset, thank you~

A RuntimeError occurs when selecting the pre-trained model of Setting1 to train Setting2, indicating that there are missing keys in the model's state_dict. I tried to use the seting1 pre-trained model you provided and this error also occurred. There was a problem loading the pre-trained model into the UNet network. I wonder why this error occured.

Hello！Do you have the outdoor-rain test set? I downloaded it from the original paper and only saw the training set, not the test set. If not, how did you deal with it?

Hi, thanks for your work! May I know how many GPUs (also which type) you used and how long it tasks to train the model?

Could you please upload the dataset_pairs_wRandomSample_ForAug3 file in the repository? The training_Setting1_wDP_Stage2.py file cannot run without this file.

Also, could you upload the code for training your model using Settings 2 and 3?

Thank you for your code. May I ask which pre-trained vgg model is used during the training process?

Hi, you have done a good job. But there is one question that puzzles me：

I can't find this file in directory 'datasets'. Do you mean dataset_pairs_wRandomSample_Triplet_txt.py?

Thank you for your contribution. The forward function outputs z+x, representing the clean image, where z acts as the compensatory element for the noise, akin to its negative value. For semantic segmentation tasks, should I solely utilize the feature map z without needing to combine it with x to form z+x? Is my understanding correct?

Hello, I'm very interested in your work and like to know how to draw this graph.

scheduler_B1.module.step(epoch)
你好，请问上面的.module来自哪里，具体的作用是什么，谢谢！

Could you provide the requirements for your code please?

请问这里面的txt是什么样子的