Comments (5)
@Ir1d The reason for using a pretraining in the DIV2K dataset is to match the performance of our modified baseline (see appendix) to the original paper's result for the fair comparison.
But since all the backbone networks (CARN, RCAN, EDSR) don't report RealSR results, we didn't use pretraining for simplicity. And I think that obviously, pretraining improves the RealSR as well.
from cutblur.
@Ir1d Do you mean detailed hyperparameter settings used in "Giving HR inputs during training" experiment? As in the appendix, we provide HR inputs instead of LR ones with 33% probability.
from cutblur.
Hi.
Multi-scale training (or X2 pretraining) is a very common strategy in recent SR methods (include models we used such as CARN, EDSR, and RCAN).
We also observed that not using X2 pretraining harms the performance of the X4 scale, perhaps it because 1) X2 pretraining provides good initialization 2) it gives additional image pairs. You can find a more detailed explanation in VDSR or EDSR paper.
from cutblur.
Hi @nmhkahn thanks, but I'm still a bit curious, why is it not neccessary for RealSR dataset, is it because RealSR didn't provide x2 downscaled images 😄
from cutblur.
Hi @nmhkahn , can you share your supplementary file? I'm interested in section "CutBlur vs. Giving HR inputs during training" but couldn't find out the exact setup of the experiment.
from cutblur.
Related Issues (20)
- image size HOT 2
- The cutout function in augments.py HOT 1
- RCAN X2 PSNR only 36.xx HOT 7
- How to use cutblur on video super resolution? HOT 1
- Training Problem HOT 2
- about cutblur function
- Why do you use nearest method for matching the resolution of (LR, HR) due to CutBlur ? HOT 7
- Is the test result the average value of multiple models? HOT 2
- question about the input shape HOT 1
- about the size of input、output and HR in the demo
- no improvement, but rather a decline HOT 1
- What is the size of the image block you use at the x2, x3, and x4 scales?
- train on custom dataset
- Loss keeps oscillating during training
- Blend & RGB channel permutation seems cause PSNR metric drop
- Pretrained model HOT 3
- Division by zero error HOT 1
- No Output and It says 0it [00:00, ?it/s] HOT 2
- Patchsize 24 HOT 1
- Train using different dataset HOT 3
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 cutblur.