Comments (9)
您好,
这个卷积层,主要是让其前面能叠加很多个residual block或者residual group,使得这样的残差结构能够训练起来。这其实是借鉴了SRResNet里面的做法(很多residual block叠加之后,以及在long skip connection之前,加一个卷积层)。
不能去除,去除的话,结果就不行了。
from rcan.
您好,
我还有一个有关学习率的疑问,除去CA模块外的部分,和EDSR的block是一致的,初期学习率是1e-4,在加上CA模块后,CA模块的学习率没有另外设置,请问这个是刚好也是1e-4合适吗,还是说CA模块的学习率无需在意?如果我更改了网络需要更改网络的学习率导致不是1e-4,我是否需要在optimizer代码里另外加上找到CA模块让其中的卷积层的学习率控制在1e-4,采用不同层不同学习率的方案?
from rcan.
您好,
无需额外设置CA的学习率,保持和其他部分一样的学习率就行。
from rcan.
您好,
我在用您的默认配置,200epoch时decay,到250epoch时loss已经能下降到3.15,我有没有必要跑完所有的1000epoch?因为GPU资源不足,如果可以的话希望直接进行下一个实验。
from rcan.
您好,
如果,你模型没有完全确定下来,你可以只跑这么多epoch。
如果,你的模型确定下来,你想跑为论文准备的结果,我建议你跑完1000个epoch。
from rcan.
Hi!
看到你在arxiv投的新文章《Residual Dense Network for Image Restoration 》,上面有关super resolution的指标比CVPR2018的版本高了不少,但是网络图看上去没有变化,想请教一下这个指标的提升是有什么策略吗?
谢谢!
from rcan.
@yulunzhang 以及F-1与F0之间的conv的必要性这个有通过对照实验验证过吗?如果是换成一个block,等于就是最早的block不加入concat而已。conv的效果肯定没有block好,我认为有点多余。
from rcan.
Hi!
看到你在arxiv投的新文章《Residual Dense Network for Image Restoration 》,上面有关super resolution的指标比CVPR2018的版本高了不少,但是网络图看上去没有变化,想请教一下这个指标的提升是有什么策略吗?
谢谢!
Hi,
Two differences:
Input size: 32x32 --> 48x48 (same as EDSR)
Training data: DIV2K --> DIV2K + Flickr2K (same as SRMDNF, D-DBPN)
from rcan.
@yulunzhang 以及F-1与F0之间的conv的必要性这个有通过对照实验验证过吗?如果是换成一个block,等于就是最早的block不加入concat而已。conv的效果肯定没有block好,我认为有点多余。
Hi,
This conv you mentioned is intended for another usage. In the current version, I didn't show it. Then, it seems to be useless.
from rcan.
Related Issues (20)
- Tips for training from scratch
- 训练的时候出现RuntimeError !! HOT 2
- how to choose the best model for test images?model_best.pt or model_latest.pt ?
- About test on Set5 dataset
- The Training time increasses while increasing the number of GPU
- About test on Set14
- How to divide the image into patches?
- NameError: ForkingPickler(file, protocol).dump(obj) name 'torch' is not definedBrokenPipeError : [Errno 32] Broken pipe
- About the calculation of PSNR
- RuntimeError:
- Understanding the whole process
- RCAN: tail module
- Can you provide the change curve of psnr during your training?
- batchsize=1
- How do self-ensemble
- The output value explode
- PSNR Problem
- Baidu download link in the “The whole test pipeline” is not useful
- 为什么使用--chop和不使用--chop得到的结果不一样
- 训练中断了,我应该修改哪里的代码继续训练
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 rcan.