Comments (4)
The vast majority of depths lie within the range [0, 300]:
Only 8 pixels have depths that exceed this (0.0000003456858%). I think normalising by dividing by 300 and clipping to [0, 1] is sufficient. This has the advantage that the depth labels are still linearly scaled, and interpretation is easy.
Do we want to alter the distribution? For example, make it uniform or Gaussian?
from hamlyn2021.
Thanks for looking at this - nice analysis. For now lets not alter the distribution? Seems like a highly skewed learning problem, looking at the peak and distr, will be interesting if learnable as is?
from hamlyn2021.
Wait, are there functions to get rid of the pixels past 300 depth? I meant more as in the distribution after what you said.
from hamlyn2021.
The depths > 300 are now clipped to 300
from hamlyn2021.
Related Issues (4)
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 hamlyn2021.