Comments (4)
As the same as previous works such as KernelGAN, IKC, and DAN, we didn't add noises in the anisotropic setting. However, if you want to evaluate our method on noisy images, you should modify the setting (in the options file) as follows and re-train the model:
degradation:
random_kernel: True
ksize: 21
code_length: 10
sig_min: 0.2
sig_max: 4.0
rate_iso: 1.0
random_disturb: false
######### add noises ###########
noise: True
# noise_high: 0.0588 # noise level 15: 15 / 255.
noise_high: 0.1176 # noise level 30: 30 / 255.
################################
from dcls-sr.
from dcls-sr.
It's different from what you describe in the paper?
from dcls-sr.
@xiab3369 Thanks for pointing it out! This is my writing mistake that the noises are only added to the isotropic setting as shown in Table 2. I will be happy to revise it in a new ArXiv version.
And if you want to try some additional experiments on noises, you could just modify the options file as I mentioned above. Thanks again and good luck!
from dcls-sr.
Related Issues (20)
- 算法相关问题 HOT 2
- 关于3090用torch1.8跑rfft和irfft如何改动,我自己改动后不报错但现在loss一直是nan。 HOT 6
- 关于setting2的测试情况 HOT 5
- 关于噪声数据集的问题 HOT 6
- 关于模糊核的对比实验 HOT 11
- 关于预训练模型 HOT 2
- 关于模糊和采样的顺序问题 HOT 2
- 关于重构的公式内的傅里叶变换 HOT 4
- 关于对比方法的问题 HOT 4
- mismatch size of tensor HOT 1
- 关于feature的问题 HOT 4
- 关于Deep Constrained Least Squares理论问题 HOT 2
- 關於train時發生的錯誤問題 HOT 12
- 关于公式9的问题 HOT 6
- 训练效果越来越差 HOT 2
- 拉普拉斯算子p HOT 1
- 关于怎么给图片添加噪声的问题 HOT 2
- 为什么训练时的模糊核,X2 、X3、X4的方差设置为[0.2,2] [0.2,3] [0.2,4] HOT 2
- 去模糊特徵圖R的可視化圖 HOT 7
- 关于训练时psnr提高不多的问题 HOT 13
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 dcls-sr.