Comments (4)
Thanks for your attention.
1.
If adapting ClassSR to the denoise task, you may need to take care of the training patch size. SR models process images in a low resolution and upsample them at the end of a network, but denoise models process images in the same resolution as GT. It brings much computational consumption.
2.
Firstly, you need well-trained branches, which all can process the corresponding input well. I guess this phenomenon is caused by the branches is not good enough for the corresponding inputs (check the branches performance) or the missing match of branches and inputs (100k+ iters training of classifier should be enough).
from classsr.
Thank you very much for your detailed reply!
- If I reduce the patch size, will it affect the result performance?
- In fact, I have pre trained the branch model, and their PSNR values are 39.3/39.7/39.9 respectively. However, the PSNR of the 30000 iter testing is only 38.3. I don't understand this phenomenon. Should I check my code?
from classsr.
- It will bring a little performance drop.
- It is normal. You test the branches in sub-images and evaluate the whole ClassSR model on another complete image, this operation causes the difference. You can compare (testing them on same test images) the ClassSR model and the most complex branches (trained with all data) to observe the performance.
from classsr.
I will do as you suggest! Thank you very much for your reply!
from classsr.
Related Issues (20)
- 超分后图像尺寸问题 HOT 6
- Perhaps the CARN model is incorrectly implemented? HOT 6
- divide_train.log 的问题 HOT 1
- tensor问题 HOT 2
- 请问一下论文里提到的baseline的结果是如何获得的? HOT 2
- 模型参数量 HOT 1
- 请问可以公布checkpoint吗 HOT 1
- 这个训练所有的模型需要多久 HOT 1
- 计算FLOPs相关 HOT 1
- 训练第三步 HOT 16
- 想问下分类网络的权重怎么获得 HOT 1
- Questions about classification method HOT 1
- 一个关于class module和probability vector的问题 HOT 1
- 关于PSNR测量问题 HOT 1
- 请问当训练ClassSR时,它联合训练的模型参数没有被optimize,导致只有class_loss下降,这种情况是否正常?如果异常,怎样修改呢? HOT 4
- I need to create my divide_ train.log HOT 1
- 请问块效应是如何解决的 HOT 2
- How to test
- How can we get the dataset DIV8K HOT 5
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 classsr.