Comments (1)
You can find the information regarding your question in the following issue. If you check the codes used for training the model, you can see that the MSE loss is normalized per pixel, therefore its value is significantly smaller than 1. Please note that all losses are printed during the training, therefore one can monitor their ranges when running the model.
from pynet.
Related Issues (17)
- can you split the datasets into small patches? HOT 1
- cannot train with mutil gpus HOT 1
- Can PyNET support other sensor filter? HOT 1
- EBB Dataset HOT 2
- Hi there, Something is wrong with the Loss... HOT 1
- download your pre-trained PyNET model HOT 3
- How to get Bayer Photo by phone?
- How to download the pre-trained model?Why I can not do it?
- why google Drive no return?
- about the data bits depth and normalization HOT 2
- How could I test on common 3 channel RGB images? HOT 1
- Cannot download dataset from Google Drive HOT 26
- level_5 module HOT 2
- Last level training HOT 4
- How to get the gt of different level when training? HOT 1
- PyNET image quality HOT 1
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 pynet.