Comments (4)
In all our reported experiments, res scale is set to 1.0 by default. Thus this trick is not reported in our factsheet.
Although the res scale trick is wield, I guess it could help when your SR network is extremely large. Another reference is the paper about training ImageNet in one hour in which authors claim that setting the scale of last BN in a residual block to zero helps overall performance.
from wdsr_ntire2018.
@JiahuiYu Thanks for your reply. The value of n_feats and block_feats are 32 and 128 in your experiment and you use res_scale with 1.0. when the n_feats in EDSR is 256 , they set res_scale to be 0.1. Compared with EDSR, I plan to set n_feats and block_feats to be 128 and 512. Then do you have advice about res_scale when the value of n_feats and block_feats are so big?
Best~~
from wdsr_ntire2018.
If you use relatively reasonable depth, eg., 16 residual blocks, using 1.0 should be fine. If the depth is crazy like 32 or 64, probably you will need to use 0.1. My experience is that using res scale only brings slight performsnce gain.
It is a good question though, and worth investigating. The trick of res scale is a mystery so far.
from wdsr_ntire2018.
got it~~ thanks~~
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.