Comments (2)
Hi Daichi,
Thanks for you interest in our code!
Unfortunately our input format is more complex than that of PointNet.
As we compute the mesh levels beforehand, we have to provide them as inputs to our network.
That is, we provide Euclidean and geodesic edges in each level, as well as the pooling trace maps interconnecting these levels.
Our initial nodes in the first level consists of XYZ coordinates, RGB color values and normal information.
As each batch consists of 4 graphs of arbitrary size, we cannot use an additional batch dimension. To ensure that edge sets and pooling trace maps refer to the right nodes we find unique ids for each node in the batch. Please checkout https://github.com/JonasSchult/pytorch_geometric_fork/blob/master/torch_geometric/data/batch.py#L150 if you want to know more about this.
Please let me know if I can help you with more explanation.
Best,
Jonas
from dcm-net.
As this issue seems unactive/solved to me, I will close it now.
Feel free to reopen it when you got further questions.
Best,
Jonas
from dcm-net.
Related Issues (13)
- When are you planing to release the code? HOT 1
- Couldn't import GraphLevelDataLoader HOT 1
- How to prepare my own dataset HOT 1
- Crops for regression task
- There is no .csv file when prepare the scannet dataset
- Random rotation augmentation neglects normals
- any experiments on shapenet part dataset HOT 1
- Fail to compile Mesh Simplification Preprocessing (VCGlib) HOT 3
- vcglib - undeclared variables in apps/tridecimator HOT 1
- Where to find how to compute Euclidean neighbors? HOT 1
- Preprocessing code for S3DIS data set?
- Visualization software 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 dcm-net.