Comments (1)
Hi!
Thanks for sharing the code. I am reading the paper and found that the implementation of the point cloud transform block (aka T-Net in the original point net paper) is different from what is mentioned in the code.
In the paper, as shown in Fig. 3, the coordinate difference the k nearest neighbor and the coordinates of the point is concatenated (therefor n x k x (3+3) = n x k x 6).
However in the code, there is one additional max pooling along the number of points axis, as compared to the original point net implementation. I do not quite understand why.
If someone can enlighten me or share their thought on this, I would be very grateful.
Edit:
I think I figured out why the input of the t-net is n x k x 6 as the input already went through feature transformation defined here. However I am still puzzled by the additional max pooling operation as compared to the original point net implementation.
We initially wanted to use EdgeConv in the spatial transformer as we did for the main backbone.
from dgcnn.
Related Issues (20)
- How to implement 92.9% OA? HOT 4
- There was no model.2048.t7 file in pretrained folder.
- Can I get the final paper?
- pytorch part segmentation HOT 1
- Can we run this code in windows?
- Visualization issues
- getting 'Indexerror' in train_multi_gpu.py HOT 1
- Understanding equation #8 in research paper (Section 3.1)
- 请问你的分类模型到底是哪样的,有的有连接,有的没有!!!
- LiDAR Point Cloud Classification results not good with real data HOT 1
- Why does the pytorch version not have transform? HOT 2
- How to add more DGCNN layers in your implementation?
- Aborted (core dumped) if I process to many points at once HOT 2
- Is the input size of the first layer 6 because the input parameters are the point itself and its normals?? HOT 1
- Why is the accuracy rate so low? HOT 1
- Visualization
- ValueError: need at least one array to concatenate HOT 2
- What is the KNN distance formula implemented by pytorch HOT 1
- The network architecture in code is different from the paper?
- 数据可视化严重问题
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 dgcnn.