Comments (5)
For example, I set the scale of self.aa1() and FeatureMatching to 4 ,but failed
from dcsr.
Hi,
For 4x SR, the scale of ref image is 4x of that of LR images. So we also need to modify the feature extractor (pretrained vgg) accordingly. The key is to make sure the feature map sizes of Ref and LR are the same so that we can calculate patch-wise cosine similarity. For example, we modified 7 to 11 in this line:
Line 26 in 70ff906
And other lines specified on 2x SR should also be modified, like shape_out*4. It can be a little tedious.
Line 110 in 70ff906
from dcsr.
Hi, For 4x SR, the scale of ref image is 4x of that of LR images. So we also need to modify the feature extractor (pretrained vgg) accordingly. The key is to make sure the feature map sizes of Ref and LR are the same so that we can calculate patch-wise cosine similarity. For example, we modified 7 to 11 in this line:
Line 26 in 70ff906
And other lines specified on 2x SR should also be modified, like shape_out*4. It can be a little tedious.
Line 110 in 70ff906
Maybe you mean " for x in range(10):"? Because when modified 7 to 11 ,it will cause channels error .Besides, if I follow the above method to modify parameters, can I train on the CUFED5x4 to get the same results as in the paper?
from dcsr.
Hi, For 4x SR, the scale of ref image is 4x of that of LR images. So we also need to modify the feature extractor (pretrained vgg) accordingly. The key is to make sure the feature map sizes of Ref and LR are the same so that we can calculate patch-wise cosine similarity. For example, we modified 7 to 11 in this line:
Line 26 in 70ff906
And other lines specified on 2x SR should also be modified, like shape_out*4. It can be a little tedious.
Line 110 in 70ff906
May I ask for the settings that train on the CUFED5 ? I want to reproduce the same result as in the paper.
from dcsr.
from dcsr.
Related Issues (20)
- How much memory does (train)test need(for CUFED5)? HOT 1
- question on dcsr.py HOT 5
- Question on patch_size HOT 1
- Train on the CUFED5 HOT 4
- Hi,
- Question about 4X SR on CUFED5 HOT 7
- Sorry I'm asking stupid questions again HOT 3
- About patch_select HOT 2
- Pretrained model on CUFED5 HOT 2
- About CameraFusion dataset HOT 4
- train,val and test
- Hi,Can you provide the testset CUFED5 for the pre-train model?
- RuntimeError: CUDA error: device-side assert triggered HOT 11
- About quick start on 4k start HOT 2
- Question on evaluation in the main paper HOT 2
- Question on network architecture HOT 4
- Question on alignment.py HOT 4
- Question on SRA Loss implementation HOT 2
- cannot reproduce 8k result as shown in the paper 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 dcsr.