Comments (2)
The general idea is to feed the trained M-Net with the global coordinates to estimate the corresponding occupancy probabilities.
Taking the 2D case as an example, you can
(1) sample a set of points from each point cloud (unoccupied points together with the observed points clouds). You may want to sample a large number of points to cover the environment as much as possible
(2) transform those points into the global frame using the poses estimated from the trained L-Net
(3) use the trained M-Net to estimate the occupancy probabilities
(4) covert the 2D global coordinates to the pixel coordinates and generate the occupancy map from the estimated probabilities and the pixel coordinates.
from deepmapping.
Hi,
Thanks for your quick reply.
I solved this problem now. Actually, this part of function is pretty similar to "self.occp_prob = self.occup_net(inputs)" in your training.
While, on the way to solve this problem. I found sth interesting for your code design, which I will posted it in a different Issues.
this one is closed.
from deepmapping.
Related Issues (12)
- run_train_2D.sh error HOT 3
- Question about the warm start HOT 2
- About the AVD traning dataset HOT 4
- who can tell me how to deal this problem? HOT 6
- run_train_2D.sh error HOT 3
- About used Active Vision Dataset (AVD) trajectory HOT 9
- Training for ordered / un-ordered data points HOT 2
- how to understand “we do not necessarily expect the trained DNNs to generalize to other scenes.” HOT 4
- About generating 3D ground truth for custom trajectory on the AVD dataset HOT 1
- why the output of M-Net is not using sigmoid? HOT 1
- A Potential Bug in Sample Unoccupied Point HOT 3
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 deepmapping.