Comments (9)
It's just for simplicity. In my opinion, two implementations are similar intrinsically.
from spsr.
Can I communicate with you in Chinese?(哈哈,我能和你用中文交流吗?)我有些疑问,SPSR的梯度分支本质上应该是求图像的梯度,按照数字图像处理的方法,应该是将彩色图转为灰度图,再求其的梯度图才是正常的流程。你在SPSR代码里面,是将RGB三个通道分别拆开,分别求其梯度图,这样每个通道的梯度图不一定一样,最后再concat到一起,会不会导致图像的边缘信息(高频信息)更凌乱or模糊?请问你有测试过单通道和三通道分别求的梯度图,有什么差别吗?
from spsr.
concat的话能保留更多的信息,一般不会导致信息变差。两种实现我们也都试过,差别很小。
from spsr.
(⊙o⊙)太棒了,我又可以省去做验证的时间了!十分感谢你
from spsr.
哈哈哈,不客气
from spsr.
hi!你好鸭,我有个小问题想请教你,你的SR分支和梯度分支的loss是相加起来,loss=sr_loss+grad_loss,这样同时求反向传播和分别backward应该是存在差别的,你有试过分开backward吗?
from spsr.
如果我需要将两个loss分开backward的话,需要两个optimizer吗?
from spsr.
我觉得怎么实现都可以,合理就行
from spsr.
好的,十分感谢你~
from spsr.
Related Issues (20)
- 模型的训练是如何安排的? HOT 3
- RuntimeError: stack expects each tensor to be equal size, but got [3, 0, 0] at entry 0 and [3, 164, 0] at entry 1
- 关于梯度图 HOT 2
- About evaluation toolbox configuration. HOT 1
- 关于root中的path HOT 3
- I am running out of memory on gpu HOT 3
- Errors accur when using evaluation tool box HOT 1
- Cannot reproduce the reported performance using the pretrained checkpoint HOT 1
- 训练时预处理的lmdb部分报错 HOT 1
- 您好,我在运行您的代码的时候遇到一个问题,期待您的答复,谢谢。在运行时,可以正常训练,但是验证时,会爆显存RuntimeError:CUDA out of memory。请问是什么原因呢 HOT 4
- Test with multiple GPUs HOT 3
- blank image HOT 6
- CUDA Out Of Memory on 4900th iteration. HOT 2
- waring HOT 2
- get a Error while run generate_dataset.py.
- question about test HOT 3
- Evaluation code modification suggestion
- 关于使用工具箱测试自己的模型 HOT 1
- create model.py is not inside models folder
- About HR_size and CUDA memory
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 spsr.