lintaopeng / u-shape_transformer_for_underwater_image_enhancement Goto Github PK
View Code? Open in Web Editor NEWU-shape Transformer for Underwater Image Enhancement
License: MIT License
U-shape Transformer for Underwater Image Enhancement
License: MIT License
您好,感谢您和您团队的贡献。能否将您训练和测试使用的数据集发我一份呢?我的邮箱是:[email protected].
祝:科研进步,身体健康。
I would like to explore the LSUI dataset, but I cannot figure out a way to download it. Please let me know the steps for downloading it.
如果想修改成输出和原图尺寸相同该如何修改呢?
In net/utils.py
, the compare_psnr
function from skimage.measure.simple_metrics
has been removed by skimage causing the code to not run.
这真是一个非常棒的工作!对水下图像的增强效果很好。请问可以提供一下UCIQE和UIQM的实现代码吗?如果可以,学生感激不尽
感谢作者精彩的工作,请问作者方便提供一下数据集LSUI的语义分割图像数据吗?万分感谢!
请问您发布的数据库来自多个已有的数据集,是否还能将UIEB,EUVP作为测试集呢?
Hello!
Is it possible for you to share the dataset to be used only for academic purposes?
Cheers
Why is it suggested to train the first 600 epochs with L2 and the last 200 with L1?
感谢您提供的优质方法,我想使用LSUI数据集进行下一步的语义分割实验,能否提供一下语义分割的图像来进行实验呢
您好,我使用您的计算UIQM和UCIQE的代码在UIEB无参照的60张图片上进行了计算,即您的论文 TABLE IV 中的第一行,但是计算的结果和论文的结果差异巨大,请问是我有什么参数或者细节弄错了吗?计算的代码是您项目中的 .ipynb_checkpoints/test_无参考-checkpoint.ipynb
请问网络训练总共需要多长时间,因为在transformer模块会涉及图像拼接,会不会出现棋盘效应呢?
您好,我看到您在论文中报告了UIEB相关指标,这个数据集没有官方的训练集和测试集的划分,我像请问您是如何划分的数据集呢?在您论文中,其他算法的结果是您自己在您划分的数据集上跑了一下,还是怎么得到的呢?
Hi, I am a newbie, can I output only 216*216 images with the weights you provided?
Could you please provide information on the actual depth measurements for the LSUI dataset?
can you provide the pre-trained model by Train-U and test dataset including Test-L504 and Test-U90?
Could I kindly inquire if it would be possible to access the lists of images utilized during the training and testing stages, for academic purposes?
论文中配图无水印但是下载的数据集带水印,能提供无水印的版本吗
你好,我想问问第一次训练是用train.ipynb, 那trainL1是什么时候用呢
I would like to count the evaluation indicators of the output image after reasoning, is there a code for calculation?
请问您划分的训练和测试的真实数据在哪里呢
请问为什么我按照您的要求来操作测试的结果差距还挺大,psnr能测试高点但是我的SSIM测试的结果却很低
Hello I am from India. I dont have the Baidu access.
Is there any other source for the Dataset?
您好,请问 LSUI 数据集下载的百度网盘提取码是什么。我已经发送邮件了,但还未收到回复
感谢你们提出的优秀的方法,请问能否提供分割数据集和介质传输图,用于后续的学习和实习
I Tried installing scikit-image still facing no module
ModuleNotFoundError Traceback (most recent call last)
Cell In[15], line 16
14 from net.Ushape_Trans import *
15 #from dataset import prepare_data, Dataset
---> 16 from net.utils import *
17 import cv2
18 import matplotlib.pyplot as plt
3 import torch.nn as nn
4 import numpy as np
----> 5 from skimage.measure.simple_metrics import compare_psnr
6 from torchvision import models
9 def weights_init_kaiming(m):
ModuleNotFoundError: No module named 'skimage.measure.simple_metrics'
你的LSUI数据集下载连接中只有raw和GT,能否上传完整的数据(包括传输图和语义分割图)呢
Can you provide your image lists in the training and testing stage? The samples in the test folder are not all of the testing data.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.