Comments (16)
SwinIR has not been tested on deraining yet, but it should be able to generalize to different restoration tasks.
from swinir.
SwinIR has not been tested on deraining yet, but it should be able to generalize to different restoration tasks.
ok 谢谢
from swinir.
Feel free to open it if you have more questions
from swinir.
hi,when i test denosing,shows the following error. how to slove it? thanks
from swinir.
Incorrect image path.
from swinir.
Incorrect image path.
from swinir.
from swinir.
It seems that you are using Windows. I guess the path may not be correct (Windows may use \\ instead of / for file path). Could you please add
print(path)
below this line?
Line 60 in c24fb46
from swinir.
ok it work,thanks!
but i have a question,from the Visual comparison,SwinIR seems the image is more smooth, 这就是处理过后的效果吗?
from swinir.
为了方便我还是用中文跟您交流吧。还有一个问题就是,您认为什么任务对于去雨的泛化效果最好?
from swinir.
For the first question, what are the compared methods? What is your setting?
For the second question, I think if you wanna test it on deraining, train it on deraining datasets.
from swinir.
For the first question, what are the compared methods? What is your setting?
For the second question, I think if you wanna test it on deraining, train it on deraining datasets.
第一个问题我意思是如图所示,第一幅图是您的测试数据集McMaster里的图片,第二幅图是测试出的result图,我的问题是:结果图看起来比测试图像更平滑了,这就是本方法的复原效果吗?
from swinir.
Since SwinIR is only trained by L1 loss in this case, blurry results are expected. If you want to make it be sharp, you can add GAN loss and perceptual loss as in real-world image SR.
from swinir.
ok i got it!您的方法非常具有研究性,我会继续深入研究,后续一定会有很多问题值得和您讨论。非常感谢!
from swinir.
hi,经过几天的研究, 我带着问题回来了。根据您的建议,我重新对模型进行训练。我使用1200对图像进行训练,我的训练日志如下txt文件,我设置的dataset_type:dncnn,由于设备条件限制,我设置了numwork==0,batch_size==1,为了快速查看模型效果,我设置了100个epoch,一共训练九个小时,训练出结果显示,对于去雨并无效果(是我的训练设置出问题了吗?)我的trainH全是高清图像,trainL是加了雨纹的图像,如果我按照要求将图像成对的训练,我把dataset_type改成plain,但是它报错了,如下图所示,我该如何解决?
trainlog.txt
from swinir.
hi,经过几天的研究, 我带着问题回来了。根据您的建议,我重新对模型进行训练。我使用1200对图像进行训练,我的训练日志如下txt文件,我设置的dataset_type:dncnn,由于设备条件限制,我设置了numwork==0,batch_size==1,为了快速查看模型效果,我设置了100个epoch,一共训练九个小时,训练出结果显示,对于去雨并无效果(是我的训练设置出问题了吗?)我的trainH全是高清图像,trainL是加了雨纹的图像,如果我按照要求将图像成对的训练,我把dataset_type改成plain,但是它报错了,如下图所示,我该如何解决? trainlog.txt
你好,可以交流一下关于去雨的训练代码吗
from swinir.
Related Issues (20)
- Colab notebook error
- About self-ensemble strategy
- not compatible with the latest cog version
- Did you train SwinIR on DIV test set?
- How to disable using two GPUs for training?
- only 1 swin layer in the RSTB module?
- It seems SwinIR doesn't use patch merging. HOT 2
- Loading pretrained weight achiving not accurate result HOT 1
- Error(s) in loading state_dict for SwinIR HOT 5
- Inquiry about patch embedding HOT 4
- 关于X8的测试集
- JPEG Artifact Removal window size
- Transfer Learning with SWINIR model
- Artifact SWINIR (training Model as Generator GAN) HOT 1
- dynamic shape inference with onnx model HOT 1
- The noise removal command eats up my entire RAM and then gets killed HOT 5
- Load model takes forever
- SWINIR as Generator in GAN : Real world
- Unable to load pretrained model
- change the video card to run on the site replicate HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from swinir.