Comments (2)
Sorry, the training code will not be included any time soon. I don't have my old code and the re-writing + training + documentation would take a lot of time, which I don't have at the moment.
The training procedure for the depth estimation network is described in:
https://link.springer.com/chapter/10.1007%2F978-3-319-98678-4_38
There is nothing unconventional about training a model for segmentation, so there are lots of good blog posts and example code out there.
In this repo, I used the same network structure for the depth prediction and the segmentation (except the final layer) and the same hyperparameters worked pretty well. If I remember correctly, I used Adam optimizer + I weighted the classes using median frequency weighting (see https://arxiv.org/pdf/1411.4734.pdf) in the loss function. Everything else is pretty standard.
from 3d_scene_reconstruction_cnns.
Thank u very much!
from 3d_scene_reconstruction_cnns.
Related Issues (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 3d_scene_reconstruction_cnns.