Comments (6)
Did you mean L2 loss is around 1000? tv loss is around 10^6? In tv loss(local smooth loss) function, the input is origin image, the output is the illumination map. Actually, during my training process, the loss is around 0.033. I suggest you can only use the input image pixel divide illumination map at first, then calculate the l2 loss between the predicted image and ground truth. Only use l2 loss and make sure the loss is right at first.
from deepupe.
Could you make sure metrics.py tv-loss code?
from deepupe.
It is the local smoothness code, not standard tv loss.
from deepupe.
The second parameter is not a predicted image, it is the illumination map.
from deepupe.
Actually I calculate illumination map with
S=min(1.0,max(im1d,im1d./(im2d+0.0001)));
You mean the second parameter not like this? In metrics.py, you use tf.image.rbg_to_grayscale, this function get 1-channal output
from deepupe.
You forgot to calculate the mean. tf.reduce_mean. and during processing image, the scale is 0-1.
from deepupe.
Related Issues (20)
- about more infomation HOT 3
- The url of downloading test dataset cannot work HOT 3
- The result is not satisfactory because PSNR reaches about 23? What Happened? HOT 3
- realease of dataset HOT 2
- 关于test数据集?
- Color Loss
- Tensorflow only use CPU version, so how should i modify the makefile? HOT 1
- I got an error when i run the run.py HOT 1
- Does not work HOT 1
- Installation Guide HOT 6
- Another reconstruction loss? HOT 1
- No op named BilateralSliceApply in defined operations. HOT 1
- 只能在Linux下运行么?(does it run on Linux? )
- Fatal error: third_party/array/array.h: No such file or directory HOT 3
- Would you please release the training code and the dataset?
- Could you please release the training code and the dataset?
- Can i get access to training code HOT 2
- brightness adjustment
- brightness adjust
- The download link for the test data is unaccessible
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 deepupe.