Comments (13)
@suke27 For x3 SR and x4 SR, you can adjust channel numbers accordingly as you like. We did lots of experiments: as long as you have wide activation (x6 - x9 wider than residual identity pathway), the performance is generally better compared with normal EDSR under same FLOPs and Params.
from wdsr_ntire2018.
@JiahuiYu, I just try x6 case in x3 and x4 SR case, found the psnr is lower than EDSR baseline(16 res+64 filter), so I ask about it. by the way, x6-x9, is there linear scale between scale time and enlarge channel.
like x2 case enlarge x6, x3 case enlarge x9, x4 case enlarge x12?
from wdsr_ntire2018.
You don't need to open new issue, let's make it clean so that others can also have a clear reference. Just reply here and I can see it.
Can you report your EDSR and WDSR in terms of (1) number of parameters, (2) channel number in residual identity path way, (3) channel number before activation, and (4) their final performance?
For x2SR, x3SR or x4SR, we use same x4 wider activation with WDSR-A, x6-x9 wider activation with WDSR-B. DO NOT use x6-x9 with WDSR-A, and DO NOT go over x9, that will make your identity pathway too slim.
from wdsr_ntire2018.
EDSR baseline 16 resblock filter 64, WDSR_A 16resblock filter 32->32*4->32, wdsr_b 16 resblock filter 32->192(1x1)->25(1x1)->32
test set: x4 case, DIV2K val dataset(801-900), psnr EDSR baseline 28.84, wdsr_a 28.77, wdsr_b 28.37
psnr computing method, SKImage compare_psnr
from wdsr_ntire2018.
One of our finding is to set the identity pathway at least SxSx3, where 3 represents for RGB, S represents SR scaling. In this case, 4x4x3 = 48.
Can you try to run quick experiments with resBlocks 8 or fewer, baseline EDSR 96 channels, and its correspondent WDSR-A, WDSR-B?
from wdsr_ntire2018.
@JiahuiYu, correct, the upsample layer just set as you said SxSx3, seems in wdsr paper, 4 Experimental Results, just compare 8 blocks in x2 case. do you have x3 or x4 experimental result. I just want to confirm my test result.
from wdsr_ntire2018.
@suke27 I meant to set residual identity pathway SxSx3 (not only the upsample layer) and re-run a quick experiment. Your previous experiment has 32->192(1x1)->25(1x1)->32, which is slim for x4 SR. It was one year ago when we ran x3 and x4 experiments, our result was that WDSR-B is better than WDSR-A, both of which is better than EDSR on x3, x4 and x8 SR.
from wdsr_ntire2018.
if my experiment is slim for x4, could you share what is your resblock for x4 case.
from wdsr_ntire2018.
Please try a quick experiment with resBlocks 8, baseline EDSR 96 channels, and its correspondent WDSR-A, WDSR-B, as I ready tell you in a earlier reply...
from wdsr_ntire2018.
you mean 8 resblock, resblock unit:96->96x6(1x1)->96x0.8->96. like that?
from wdsr_ntire2018.
WDSR-B with 48->48x6(1x1)->48x0.8->48, and EDSR with 96->96. Please double check the #parameters are fair.
By the way, which backbone are you using for training? Can you reproduce our results in x2SR?
from wdsr_ntire2018.
Thank you for your answer, and happy Chinese new year to you! I will try, by the way, do you have -DIV2k- dataset (realistic training dataset)?, I want to try in track 2,3,4 training dataset
from wdsr_ntire2018.
Hi I don’t think I have permission to distribute their dataset. Please ask NTIRE for help. You can also have a look on colab competition page and see if you can get download link.
from wdsr_ntire2018.
Related Issues (20)
- Testing the models HOT 4
- Testing on "wild LR" = track 3 NTIRE2018 HOT 1
- How to reduce inference time HOT 1
- I didn't get desired training result HOT 3
- An error when training with my own dataset with scale 3 or 4 HOT 1
- How to achieve the results in the paper? HOT 1
- preprocess for training data HOT 1
- About the linear low-rank convolution HOT 1
- loss suddenly turned into nan HOT 1
- Some conceptual questions HOT 3
- Where weight normalization is used? HOT 1
- I got a result image of all gray with no contents HOT 3
- What does this do? x = (x - self.rgb_mean.cuda()*255)/127.5 HOT 1
- Ablation study for WDSR-B HOT 1
- There is not the second act layer in WDSR-B between the 3x3 Conv and the second 1x1 Conv, why? HOT 1
- In WDSR-B, why not do the 3x3 Conv without the second 1x1 Conv? HOT 1
- in forward of wdsr.py, where dose 127.5 come from? HOT 4
- Pytorch pretrained model for WDSR HOT 1
- Weight normalization during inference. HOT 1
- Custom dataset training
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 wdsr_ntire2018.