2022-CVPR-AirNet

2022-CVPR-AirNet copied to clipboard

About the all-in-one training details

1

Hi, I am confusing about the "In other words, AirNet under AIO is the model trained on the collection of all the datasets that consists of three corruptions (i.e., noise,...

huang-hz

I am very interested in this paper, but I have developed some alienation while reading the code. May I ask how many 2080Ti gpus were used for training in this...

Vocal-map

Dataset partitioning issues!!!

1

Hello, professors, How to generate the path of the training dataset and store the path in the corresponding document? Thanks!

cvor1

I have a question about the dataset generating process.

1

Before the question, I really thank you for the great research on multi degradation restoration. But while reading your paper, I was curious on two things. 1. You generated the...

penguin1109

Hello, professors, How to generate the path of the training dataset and store the path in the corresponding document? Thanks!

cvor1

请问可以直接提供Rain100H和Rain100L的去雨结果吗？

1

hotdjboy

Hi. I found that the MoCo model in your implementation will not call the batch_shuffle_ddp() and batch_unshuffle_ddp before and after normalizing. Could you explain the reason? Will these two functions...

VongolaWu

Hi,I'm very interested in this paper. I am confused about how to divide the data set. If possible, can you share the data set for the experiment. Looking forward to...

Nancy23333

About combined degradations

1

Thanks for your excellent work! Also, may I ask if you've tried training AirNet on images with multiple degradations that simultaneously present in one image? Do you think this is...

Kaiwen-Zhu

problem of "conda env create -f airnet.yaml"

1

 Like above image, this command don't work in Ubuntu 20.04.6 LTS

LouisCodingMachine